Second push!

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedc7184731798367d39eae56f5314a9b5f1b47cb967744cb3dba253b6407548
+oid sha256:e839526bd38d1666aa719a1d9650437247f6dc0cc0534b2b99ef0c6bf86268ee
 size 1418184

Pyramids/{Pyramids-499979.onnx → Pyramids-1000075.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedc7184731798367d39eae56f5314a9b5f1b47cb967744cb3dba253b6407548
+oid sha256:e839526bd38d1666aa719a1d9650437247f6dc0cc0534b2b99ef0c6bf86268ee
 size 1418184

Pyramids/{Pyramids-499979.pt → Pyramids-1000075.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2fe7b60ed8543b50637d22d5fe2de176f39a62e8cca0b1cad79f907873d1cb
+oid sha256:be4732a07df33c67eadafd629f2b42f874151609fe392f145d3e44d79ce44a1b
 size 8650990

Pyramids/{Pyramids-500107.onnx → Pyramids-499999.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedc7184731798367d39eae56f5314a9b5f1b47cb967744cb3dba253b6407548
+oid sha256:1caeecf08679dde28fbaeb7226e537bc21758d614528bd32b0c2ecec464a74ec
 size 1418184

Pyramids/{Pyramids-500107.pt → Pyramids-499999.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c07d4b8456ca2d6baffb0079c17ba708f3e14000a2dd20888c8c2862e2aab5
+oid sha256:3fbbd2738f7af95cd439d77beabd9538a82b89e32e4dcf7845f4df1d46bb00c9
 size 8650990

Pyramids/Pyramids-999947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e839526bd38d1666aa719a1d9650437247f6dc0cc0534b2b99ef0c6bf86268ee
+size 1418184

Pyramids/Pyramids-999947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab42740deca7c8dd49fe3ce600e204fe96e60ddfb4d9c7d015d13d5b3b47db5
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c07d4b8456ca2d6baffb0079c17ba708f3e14000a2dd20888c8c2862e2aab5
+oid sha256:be4732a07df33c67eadafd629f2b42f874151609fe392f145d3e44d79ce44a1b
 size 8650990

Pyramids/{events.out.tfevents.1680017419.3c70acfe213f.8039.0 → events.out.tfevents.1680018668.3c70acfe213f.13598.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d545aa49c3938c42d436257b1e5d5ed5cf60c7efd2f9f83b43d76ffc4d139e4
-size 174770
+oid sha256:c7f7174ebc1645321b3b3be49910cc28979a6c4b076544a585645c6b40fd9dda
+size 499674

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 128, "summary_freq": 20000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 20000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 500000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 20000
     threaded: false
@@ -77,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids Training2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55110 [Flags] 2 [Guid] 1738665352 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55202 [Flags] 2 [Guid] 2930147450 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.099 seconds
+- Completed reload, in  0.086 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.745753 ms
+UnloadTime: 0.760170 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6988 frames, [32.0 KB-64.0 KB]: 1901 frames, [64.0 KB-128.0 KB]: 501 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3643 frames, [32.0 KB-64.0 KB]: 11568 frames, [64.0 KB-128.0 KB]: 3557 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9092 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11811
+  Peak main deferred allocation count 12260
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9390 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames, [32.0 MB-64.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.3 MB
+      Peak Allocated memory 32.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9391 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.5 MB
+      Peak Allocated memory 21.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9390 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 9391 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9092 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 9390 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -293,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9391 frames
+      Peak usage frame count: [0-1.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 9391 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18769 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 9391 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1680018417492,"processId":8059,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1680020882428,"processId":13614,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.7341330647468567,
-            "min": 0.6661165952682495,
-            "max": 1.5667954683303833,
-            "count": 25
+            "value": 0.2928386628627777,
+            "min": 0.2808834910392761,
+            "max": 1.5365270376205444,
+            "count": 50
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 14541.7080078125,
-            "min": 13130.490234375,
-            "max": 31486.322265625,
-            "count": 25
+            "value": 5894.2568359375,
+            "min": 5550.2578125,
+            "max": 30878.046875,
+            "count": 50
         },
         "Pyramids.Step.mean": {
-            "value": 499979.0,
+            "value": 999947.0,
             "min": 19968.0,
-            "max": 499979.0,
-            "count": 25
+            "max": 999947.0,
+            "count": 50
         },
         "Pyramids.Step.sum": {
-            "value": 499979.0,
+            "value": 999947.0,
             "min": 19968.0,
-            "max": 499979.0,
-            "count": 25
+            "max": 999947.0,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.07783125340938568,
-            "min": -0.10738036036491394,
-            "max": -0.053263675421476364,
-            "count": 25
+            "value": 0.6337957978248596,
+            "min": -0.0891326516866684,
+            "max": 0.6548319458961487,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -12.530832290649414,
-            "min": -17.288238525390625,
-            "max": -8.575451850891113,
-            "count": 25
+            "value": 121.68879699707031,
+            "min": -14.439489364624023,
+            "max": 127.27035522460938,
+            "count": 50
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.017907408997416496,
-            "min": 0.015266699716448784,
-            "max": 0.2930479347705841,
-            "count": 25
+            "value": -0.007049087900668383,
+            "min": -0.03438590094447136,
+            "max": 0.463748961687088,
+            "count": 50
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 2.8830928802490234,
-            "min": 2.4579386711120605,
-            "max": 46.59461975097656,
-            "count": 25
+            "value": -1.3534249067306519,
+            "min": -6.395777702331543,
+            "max": 73.736083984375,
+            "count": 50
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06761589899787826,
-            "min": 0.0653111275212057,
-            "max": 0.07333786892082446,
-            "count": 25
+            "value": 0.06274886612873219,
+            "min": 0.06274886612873219,
+            "max": 0.07449785151129816,
+            "count": 50
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.6761589899787827,
-            "min": 0.29123317015266326,
-            "max": 0.6761589899787827,
-            "count": 25
+            "value": 0.5647397951585897,
+            "min": 0.28386088515010977,
+            "max": 0.7197455395459353,
+            "count": 50
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0002807328444097884,
-            "min": 5.767989519985306e-05,
-            "max": 0.006750822391908535,
-            "count": 25
+            "value": 0.01632938282881952,
+            "min": 0.0009238557525356134,
+            "max": 0.017708753124533433,
+            "count": 50
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.002807328444097884,
-            "min": 0.0005191190567986776,
-            "max": 0.02700328956763414,
-            "count": 25
+            "value": 0.14696444545937568,
+            "min": 0.00831470177282052,
+            "max": 0.1664805162262044,
+            "count": 50
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.8480580506800066e-06,
-            "min": 5.8480580506800066e-06,
-            "max": 0.00029391360202879994,
-            "count": 25
+            "value": 2.875399041566666e-06,
+            "min": 2.875399041566666e-06,
+            "max": 0.0002969568010144,
+            "count": 50
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 5.848058050680007e-05,
-            "min": 5.848058050680007e-05,
-            "max": 0.0020009042330320003,
-            "count": 25
+            "value": 2.5878591374099994e-05,
+            "min": 2.5878591374099994e-05,
+            "max": 0.0025506196497934995,
+            "count": 50
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10194932000000001,
-            "min": 0.10194932000000001,
-            "max": 0.1979712,
-            "count": 25
+            "value": 0.10095843333333335,
+            "min": 0.10095843333333335,
+            "max": 0.19898559999999998,
+            "count": 50
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.0194932,
-            "min": 0.7918848,
-            "max": 1.5669680000000001,
-            "count": 25
+            "value": 0.9086259000000001,
+            "min": 0.7959423999999999,
+            "max": 1.8502064999999999,
+            "count": 50
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00020473706800000027,
-            "min": 0.00020473706800000027,
-            "max": 0.009797322879999997,
-            "count": 25
+            "value": 0.00010574748999999997,
+            "min": 0.00010574748999999997,
+            "max": 0.00989866144,
+            "count": 50
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0020473706800000027,
-            "min": 0.0020473706800000027,
-            "max": 0.06672010319999999,
-            "count": 25
+            "value": 0.0009517274099999997,
+            "min": 0.0009517274099999997,
+            "max": 0.08503562934999999,
+            "count": 50
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.018198054283857346,
-            "min": 0.018198054283857346,
-            "max": 0.49040496349334717,
-            "count": 25
+            "value": 0.013020750135183334,
+            "min": 0.012529483996331692,
+            "max": 0.7789566516876221,
+            "count": 50
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.18198055028915405,
-            "min": 0.18038246035575867,
-            "max": 1.9616198539733887,
-            "count": 25
+            "value": 0.11718675494194031,
+            "min": 0.1127653568983078,
+            "max": 3.1158266067504883,
+            "count": 50
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 999.0,
-            "min": 932.6666666666666,
+            "value": 281.61971830985914,
+            "min": 281.61971830985914,
             "max": 999.0,
-            "count": 25
+            "count": 50
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 20979.0,
-            "min": 15984.0,
-            "max": 29888.0,
-            "count": 25
+            "value": 19995.0,
+            "min": 15629.0,
+            "max": 29061.0,
+            "count": 50
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.9996952900574321,
+            "value": 1.7183802650428155,
             "min": -1.0000000521540642,
-            "max": -0.6339053064584732,
-            "count": 25
+            "max": 1.7183802650428155,
+            "count": 50
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -20.993601091206074,
-            "min": -27.916401579976082,
-            "max": -12.044200822710991,
-            "count": 25
+            "value": 122.0049988180399,
+            "min": -25.088201582431793,
+            "max": 122.0049988180399,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.9996952900574321,
+            "value": 1.7183802650428155,
             "min": -1.0000000521540642,
-            "max": -0.6339053064584732,
-            "count": 25
+            "max": 1.7183802650428155,
+            "count": 50
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -20.993601091206074,
-            "min": -27.916401579976082,
-            "max": -12.044200822710991,
-            "count": 25
+            "value": 122.0049988180399,
+            "min": -25.088201582431793,
+            "max": 122.0049988180399,
+            "count": 50
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.18796526689437174,
-            "min": 0.18796526689437174,
-            "max": 7.550496941432357,
-            "count": 25
+            "value": 0.03746965001615971,
+            "min": 0.03746965001615971,
+            "max": 12.048488164320588,
+            "count": 50
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.9472706047818065,
-            "min": 3.347864227835089,
-            "max": 120.80795106291771,
-            "count": 25
+            "value": 2.6603451511473395,
+            "min": 2.5668109870312037,
+            "max": 192.7758106291294,
+            "count": 50
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 25
+            "count": 50
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 25
+            "count": 50
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680017416",
+        "start_time_seconds": "1680018665",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1680018417"
+        "end_time_seconds": "1680020882"
     },
-    "total": 1000.670712594,
+    "total": 2216.771151455,
     "count": 1,
-    "self": 0.535452437999993,
+    "self": 0.7891267029995106,
     "children": {
         "run_training.setup": {
-            "total": 0.10528132700005699,
+            "total": 0.10739385400029278,
             "count": 1,
-            "self": 0.10528132700005699
+            "self": 0.10739385400029278
         },
         "TrainerController.start_learning": {
-            "total": 1000.0299788289999,
+            "total": 2215.8746308980003,
             "count": 1,
-            "self": 0.5761942250028369,
+            "self": 1.3153144308416813,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.998880460999999,
+                    "total": 5.9751849700001,
                     "count": 1,
-                    "self": 6.998880460999999
+                    "self": 5.9751849700001
                 },
                 "TrainerController.advance": {
-                    "total": 992.314859869997,
-                    "count": 31476,
-                    "self": 0.6505136369762567,
+                    "total": 2208.4467628901584,
+                    "count": 64174,
+                    "self": 1.412703235223944,
                     "children": {
                         "env_step": {
-                            "total": 683.1800534140225,
-                            "count": 31476,
-                            "self": 632.2829693070514,
+                            "total": 1582.0462280959287,
+                            "count": 64174,
+                            "self": 1477.2499674110236,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 50.531694535966835,
-                                    "count": 31476,
-                                    "self": 2.267776380997475,
+                                    "total": 104.0307137649529,
+                                    "count": 64174,
+                                    "self": 4.55181682294824,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 48.26391815496936,
-                                            "count": 31301,
-                                            "self": 48.26391815496936
+                                            "total": 99.47889694200467,
+                                            "count": 62563,
+                                            "self": 99.47889694200467
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3653895710042434,
-                                    "count": 31476,
+                                    "total": 0.7655469199521576,
+                                    "count": 64174,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 997.7277990040011,
-                                            "count": 31476,
+                                            "total": 2211.343897246998,
+                                            "count": 64174,
                                             "is_parallel": true,
-                                            "self": 419.7370255559872,
+                                            "self": 845.9647931480599,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001992520999920089,
+                                                            "total": 0.0018788109996421554,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006486170000243874,
+                                                            "self": 0.0006560610004271439,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013439039998957014,
+                                                                    "total": 0.0012227499992150115,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013439039998957014
+                                                                    "self": 0.0012227499992150115
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07189688499988733,
+                                                            "total": 0.04709211899989896,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007478479997189424,
+                                                            "self": 0.0005314039999575471,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004650770001717319,
+                                                                    "total": 0.0005800260000796698,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004650770001717319
+                                                                    "self": 0.0005800260000796698
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06829534000007698,
+                                                                    "total": 0.04432440899972789,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06829534000007698
+                                                                    "self": 0.04432440899972789
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0023886199999196833,
+                                                                    "total": 0.0016562800001338474,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005257729999357252,
+                                                                    "self": 0.0003438699995967909,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001862846999983958,
+                                                                            "total": 0.0013124100005370565,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001862846999983958
+                                                                            "self": 0.0013124100005370565
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 577.9907734480139,
-                                                    "count": 31475,
+                                                    "total": 1365.3791040989381,
+                                                    "count": 64173,
                                                     "is_parallel": true,
-                                                    "self": 15.285572660031676,
+                                                    "self": 30.698590465921825,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 11.203046406035355,
-                                                            "count": 31475,
+                                                            "total": 22.294069002011383,
+                                                            "count": 64173,
                                                             "is_parallel": true,
-                                                            "self": 11.203046406035355
+                                                            "self": 22.294069002011383
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 506.6390823089903,
-                                                            "count": 31475,
+                                                            "total": 1222.142585048945,
+                                                            "count": 64173,
                                                             "is_parallel": true,
-                                                            "self": 506.6390823089903
+                                                            "self": 1222.142585048945
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 44.863072072956584,
-                                                            "count": 31475,
+                                                            "total": 90.24385958205994,
+                                                            "count": 64173,
                                                             "is_parallel": true,
-                                                            "self": 9.33501502281456,
+                                                            "self": 18.896714161032378,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 35.528057050142024,
-                                                                    "count": 251800,
+                                                                    "total": 71.34714542102756,
+                                                                    "count": 513384,
                                                                     "is_parallel": true,
-                                                                    "self": 35.528057050142024
+                                                                    "self": 71.34714542102756
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 308.48429281899826,
-                            "count": 31476,
-                            "self": 0.9449139979631127,
+                            "total": 624.9878315590058,
+                            "count": 64174,
+                            "self": 2.5063146079914986,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 55.031415449034284,
-                                    "count": 31476,
-                                    "self": 54.86776243003442,
+                                    "total": 116.4424778490179,
+                                    "count": 64174,
+                                    "self": 116.18871289801746,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.16365301899986662,
-                                            "count": 1,
-                                            "self": 0.16365301899986662
+                                            "total": 0.2537649510004485,
+                                            "count": 2,
+                                            "self": 0.2537649510004485
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 252.50796337200086,
-                                    "count": 210,
-                                    "self": 161.7697261970161,
+                                    "total": 506.0390391019964,
+                                    "count": 458,
+                                    "self": 324.4800078670337,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 90.73823717498476,
-                                            "count": 11394,
-                                            "self": 90.73823717498476
+                                            "total": 181.55903123496273,
+                                            "count": 22749,
+                                            "self": 181.55903123496273
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2840000636060722e-06,
+                    "total": 1.5519999578827992e-06,
                     "count": 1,
-                    "self": 1.2840000636060722e-06
+                    "self": 1.5519999578827992e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.14004298899999412,
+                    "total": 0.13736705500014068,
                     "count": 1,
-                    "self": 0.0018353400000705733,
+                    "self": 0.0018593439999676775,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13820764899992355,
+                            "total": 0.135507711000173,
                             "count": 1,
-                            "self": 0.13820764899992355
+                            "self": 0.135507711000173
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499979,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499979.onnx",
-                "reward": null,
-                "creation_time": 1680018416.844014,
+                "steps": 499999,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-499999.onnx",
+                "reward": 1.5109999626874924,
+                "creation_time": 1680019717.5600991,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499979.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-499999.pt"
                 ]
             },
             {
-                "steps": 500107,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500107.onnx",
-                "reward": null,
-                "creation_time": 1680018416.99939,
+                "steps": 999947,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-999947.onnx",
+                "reward": 1.6489999629557133,
+                "creation_time": 1680020881.5172772,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500107.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-999947.pt"
+                ]
+            },
+            {
+                "steps": 1000075,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-1000075.onnx",
+                "reward": 1.6489999629557133,
+                "creation_time": 1680020881.6693883,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training2/Pyramids/Pyramids-1000075.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500107,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1680018416.99939,
+            "steps": 1000075,
+            "file_path": "results/Pyramids Training2/Pyramids.onnx",
+            "reward": 1.6489999629557133,
+            "creation_time": 1680020881.6693883,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500107.pt"
+                "results/Pyramids Training2/Pyramids/Pyramids-1000075.pt"
             ]
         }
     },