alanwsx commited on
Commit
2e69952
·
verified ·
1 Parent(s): 79e1f76

First Push

Browse files
SnowballTarget.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b584d0498001ca7470dccd13acb604da81620cf5d52818dce8b61a2c105de0
3
+ size 650646
SnowballTarget/SnowballTarget-149984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e82f486d08a1d5484e287ad9dddde1c0c3050e0690087cbd397557241ded04c
3
+ size 650646
SnowballTarget/SnowballTarget-149984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dece237c60745f4ceb81f51de29dd3db80ac9cc1d938fed353fc4583667697b
3
+ size 3850075
SnowballTarget/SnowballTarget-199984.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b584d0498001ca7470dccd13acb604da81620cf5d52818dce8b61a2c105de0
3
+ size 650646
SnowballTarget/SnowballTarget-199984.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:517dd7940549d0d4ae006db906543270853cd3270b930b40291f503c9deeb057
3
+ size 3850075
SnowballTarget/SnowballTarget-200112.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b584d0498001ca7470dccd13acb604da81620cf5d52818dce8b61a2c105de0
3
+ size 650646
SnowballTarget/SnowballTarget-200112.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0a23149cc02f6e3b68a0d684aca6e90d44d55e7b51101a9353280583b859d9
3
+ size 3850075
SnowballTarget/SnowballTarget-49936.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d296e4d696513798c56a401b01f4b6832b9ad26c1e5ac5f418123300b727976
3
+ size 650646
SnowballTarget/SnowballTarget-49936.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c39e77d61e0d046b663c8a68ba3221967bf88656c8567529620056010cb1488
3
+ size 3850000
SnowballTarget/SnowballTarget-99960.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bca590c69e280cb6f0016aea2f449dd7c0551f53abc3630a01fc76e7f46a54d
3
+ size 650646
SnowballTarget/SnowballTarget-99960.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccddcf8186b04f6ad3cd8a05711739ca55fbaf8917e0a55c285b2f3406582d9
3
+ size 3850000
SnowballTarget/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928c9272c088e8dd0a9eeab0c47ed9f632239cff37914a68e166bd0cf34a0261
3
+ size 3849250
SnowballTarget/events.out.tfevents.1736831741.ad4166b57693.16028.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516e4b080321d3601ae40567edd0d0756f2ed240a04295b31c2908aa51afacf5
3
+ size 100940
config.json CHANGED
@@ -1 +1 @@
1
- {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
 
1
+ {"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 1000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
configuration.yaml CHANGED
@@ -40,8 +40,8 @@ behaviors:
40
  even_checkpoints: false
41
  max_steps: 200000
42
  time_horizon: 64
43
- summary_freq: 10000
44
- threaded: true
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
@@ -70,7 +70,7 @@ checkpoint_settings:
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
- force: false
74
  train_model: false
75
  inference: false
76
  results_dir: results
 
40
  even_checkpoints: false
41
  max_steps: 200000
42
  time_horizon: 64
43
+ summary_freq: 1000
44
+ threaded: false
45
  self_play: null
46
  behavioral_cloning: null
47
  env_settings:
 
70
  initialize_from: null
71
  load_model: false
72
  resume: false
73
+ force: true
74
  train_model: false
75
  inference: false
76
  results_dir: results
run_logs/Player-0.log CHANGED
@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
5
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
6
- PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
7
- Unable to load player prefs
8
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
9
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
10
  Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
34
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
35
  FMOD initialized on nosound output
36
  Begin MonoManager ReloadAssembly
37
- - Completed reload, in 0.095 seconds
38
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
39
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
40
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
45
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
46
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
47
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
48
- UnloadTime: 0.858359 ms
49
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
50
  requesting resize 84 x 84
51
  Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
53
  [ALLOC_TEMP_TLS] TLS Allocator
54
  StackAllocators :
55
  [ALLOC_TEMP_MAIN]
56
- Peak usage frame count: [8.0 KB-16.0 KB]: 38 frames, [2.0 MB-4.0 MB]: 1 frames
57
  Initial Block Size 4.0 MB
58
  Current Block Size 4.0 MB
59
  Peak Allocated Bytes 2.0 MB
@@ -169,19 +166,19 @@ Memory Statistics:
169
  Peak Allocated Bytes 0 B
170
  Overflow Count 0
171
  [ALLOC_DEFAULT] Dual Thread Allocator
172
- Peak main deferred allocation count 25
173
  [ALLOC_BUCKET]
174
  Large Block size 4.0 MB
175
  Used Block count 1
176
  Peak Allocated bytes 1.0 MB
177
  [ALLOC_DEFAULT_MAIN]
178
- Peak usage frame count: [4.0 MB-8.0 MB]: 39 frames
179
  Requested Block Size 16.0 MB
180
  Peak Block count 1
181
- Peak Allocated memory 4.8 MB
182
  Peak Large allocation bytes 0 B
183
  [ALLOC_DEFAULT_THREAD]
184
- Peak usage frame count: [16.0 MB-32.0 MB]: 39 frames
185
  Requested Block Size 16.0 MB
186
  Peak Block count 1
187
  Peak Allocated memory 17.8 MB
@@ -213,13 +210,13 @@ Memory Statistics:
213
  Used Block count 1
214
  Peak Allocated bytes 1.0 MB
215
  [ALLOC_GFX_MAIN]
216
- Peak usage frame count: [32.0 KB-64.0 KB]: 35 frames, [64.0 KB-128.0 KB]: 4 frames
217
  Requested Block Size 16.0 MB
218
  Peak Block count 1
219
- Peak Allocated memory 65.6 KB
220
  Peak Large allocation bytes 0 B
221
  [ALLOC_GFX_THREAD]
222
- Peak usage frame count: [32.0 KB-64.0 KB]: 39 frames
223
  Requested Block Size 16.0 MB
224
  Peak Block count 1
225
  Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
231
  Used Block count 1
232
  Peak Allocated bytes 1.0 MB
233
  [ALLOC_CACHEOBJECTS_MAIN]
234
- Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames
235
  Requested Block Size 4.0 MB
236
  Peak Block count 1
237
  Peak Allocated memory 0.6 MB
238
  Peak Large allocation bytes 0 B
239
  [ALLOC_CACHEOBJECTS_THREAD]
240
- Peak usage frame count: [0.5 MB-1.0 MB]: 38 frames, [2.0 MB-4.0 MB]: 1 frames
241
  Requested Block Size 4.0 MB
242
  Peak Block count 1
243
  Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
249
  Used Block count 1
250
  Peak Allocated bytes 1.0 MB
251
  [ALLOC_TYPETREE_MAIN]
252
- Peak usage frame count: [0-1.0 KB]: 39 frames
253
  Requested Block Size 2.0 MB
254
  Peak Block count 1
255
  Peak Allocated memory 1.0 KB
256
  Peak Large allocation bytes 0 B
257
  [ALLOC_TYPETREE_THREAD]
258
- Peak usage frame count: [1.0 KB-2.0 KB]: 39 frames
259
  Requested Block Size 2.0 MB
260
  Peak Block count 1
261
  Peak Allocated memory 1.7 KB
 
2
  Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
3
  Preloaded 'lib_burst_generated.so'
4
  Preloaded 'libgrpc_csharp_ext.x64.so'
 
 
 
5
  Initialize engine version: 2021.3.14f1 (eee1884e7226)
6
  [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
7
  Forcing GfxDevice: Null
 
31
  FMOD failed to initialize the output device.: "Error initializing output device. " (60)
32
  FMOD initialized on nosound output
33
  Begin MonoManager ReloadAssembly
34
+ - Completed reload, in 0.084 seconds
35
  ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
36
  ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
37
  ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 
42
  WARNING: Shader Unsupported: 'Standard' - All subshaders removed
43
  WARNING: Shader Did you use #pragma only_renderers and omit this platform?
44
  WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
45
+ UnloadTime: 0.662205 ms
46
  ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
47
  requesting resize 84 x 84
48
  Setting up 1 worker threads for Enlighten.
 
50
  [ALLOC_TEMP_TLS] TLS Allocator
51
  StackAllocators :
52
  [ALLOC_TEMP_MAIN]
53
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
54
  Initial Block Size 4.0 MB
55
  Current Block Size 4.0 MB
56
  Peak Allocated Bytes 2.0 MB
 
166
  Peak Allocated Bytes 0 B
167
  Overflow Count 0
168
  [ALLOC_DEFAULT] Dual Thread Allocator
169
+ Peak main deferred allocation count 40
170
  [ALLOC_BUCKET]
171
  Large Block size 4.0 MB
172
  Used Block count 1
173
  Peak Allocated bytes 1.0 MB
174
  [ALLOC_DEFAULT_MAIN]
175
+ Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
176
  Requested Block Size 16.0 MB
177
  Peak Block count 1
178
+ Peak Allocated memory 6.6 MB
179
  Peak Large allocation bytes 0 B
180
  [ALLOC_DEFAULT_THREAD]
181
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5458 frames
182
  Requested Block Size 16.0 MB
183
  Peak Block count 1
184
  Peak Allocated memory 17.8 MB
 
210
  Used Block count 1
211
  Peak Allocated bytes 1.0 MB
212
  [ALLOC_GFX_MAIN]
213
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5142 frames, [64.0 KB-128.0 KB]: 316 frames
214
  Requested Block Size 16.0 MB
215
  Peak Block count 1
216
+ Peak Allocated memory 66.0 KB
217
  Peak Large allocation bytes 0 B
218
  [ALLOC_GFX_THREAD]
219
+ Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
220
  Requested Block Size 16.0 MB
221
  Peak Block count 1
222
  Peak Allocated memory 39.6 KB
 
228
  Used Block count 1
229
  Peak Allocated bytes 1.0 MB
230
  [ALLOC_CACHEOBJECTS_MAIN]
231
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5458 frames
232
  Requested Block Size 4.0 MB
233
  Peak Block count 1
234
  Peak Allocated memory 0.6 MB
235
  Peak Large allocation bytes 0 B
236
  [ALLOC_CACHEOBJECTS_THREAD]
237
+ Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
238
  Requested Block Size 4.0 MB
239
  Peak Block count 1
240
  Peak Allocated memory 2.2 MB
 
246
  Used Block count 1
247
  Peak Allocated bytes 1.0 MB
248
  [ALLOC_TYPETREE_MAIN]
249
+ Peak usage frame count: [0-1.0 KB]: 5458 frames
250
  Requested Block Size 2.0 MB
251
  Peak Block count 1
252
  Peak Allocated memory 1.0 KB
253
  Peak Large allocation bytes 0 B
254
  [ALLOC_TYPETREE_THREAD]
255
+ Peak usage frame count: [1.0 KB-2.0 KB]: 5458 frames
256
  Requested Block Size 2.0 MB
257
  Peak Block count 1
258
  Peak Allocated memory 1.7 KB
run_logs/timers.json CHANGED
@@ -1,68 +1,214 @@
1
  {
2
  "name": "root",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "metadata": {
4
  "timer_format_version": "0.1.0",
5
- "start_time_seconds": "1736828380",
6
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
7
- "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
8
  "mlagents_version": "1.2.0.dev0",
9
  "mlagents_envs_version": "1.2.0.dev0",
10
  "communication_protocol_version": "1.5.0",
11
  "pytorch_version": "2.5.1+cu121",
12
  "numpy_version": "1.23.5",
13
- "end_time_seconds": "1736831304"
14
  },
15
- "total": 2923.657183952,
16
  "count": 1,
17
- "self": 0.42285245399989435,
18
  "children": {
19
  "run_training.setup": {
20
- "total": 0.05899757399998862,
21
  "count": 1,
22
- "self": 0.05899757399998862
23
  },
24
  "TrainerController.start_learning": {
25
- "total": 2923.1753339240004,
26
  "count": 1,
27
- "self": 0.0036916210005983885,
28
  "children": {
29
  "TrainerController._reset_env": {
30
- "total": 5.62553995799999,
31
  "count": 1,
32
- "self": 5.62553995799999
33
  },
34
  "TrainerController.advance": {
35
- "total": 2917.5432696589996,
36
- "count": 128,
37
- "self": 0.001650475999667833,
38
  "children": {
39
  "env_step": {
40
- "total": 2917.541619183,
41
- "count": 128,
42
- "self": 2916.2190069139997,
43
  "children": {
44
  "SubprocessEnvManager._take_step": {
45
- "total": 1.3210949270003312,
46
- "count": 128,
47
- "self": 0.008665538000286688,
48
  "children": {
49
  "TorchPolicy.evaluate": {
50
- "total": 1.3124293890000445,
51
- "count": 128,
52
- "self": 1.3124293890000445
53
  }
54
  }
55
  },
56
  "workers": {
57
- "total": 0.001517341999999644,
58
- "count": 128,
59
  "self": 0.0,
60
  "children": {
61
  "worker_root": {
62
- "total": 8.674463628000069,
63
- "count": 128,
64
  "is_parallel": true,
65
- "self": 7.248302213000102,
66
  "children": {
67
  "run_training.setup": {
68
  "total": 0.0,
@@ -71,48 +217,48 @@
71
  "self": 0.0,
72
  "children": {
73
  "steps_from_proto": {
74
- "total": 0.0020915270000045894,
75
  "count": 1,
76
  "is_parallel": true,
77
- "self": 0.0006271099999253238,
78
  "children": {
79
  "_process_rank_one_or_two_observation": {
80
- "total": 0.0014644170000792656,
81
  "count": 10,
82
  "is_parallel": true,
83
- "self": 0.0014644170000792656
84
  }
85
  }
86
  },
87
  "UnityEnvironment.step": {
88
- "total": 0.03501447899998311,
89
  "count": 1,
90
  "is_parallel": true,
91
- "self": 0.0006033180000599714,
92
  "children": {
93
  "UnityEnvironment._generate_step_input": {
94
- "total": 0.0003948199999967983,
95
  "count": 1,
96
  "is_parallel": true,
97
- "self": 0.0003948199999967983
98
  },
99
  "communicator.exchange": {
100
- "total": 0.032124030999966635,
101
  "count": 1,
102
  "is_parallel": true,
103
- "self": 0.032124030999966635
104
  },
105
  "steps_from_proto": {
106
- "total": 0.001892309999959707,
107
  "count": 1,
108
  "is_parallel": true,
109
- "self": 0.00036987899989071593,
110
  "children": {
111
  "_process_rank_one_or_two_observation": {
112
- "total": 0.0015224310000689911,
113
  "count": 10,
114
  "is_parallel": true,
115
- "self": 0.0015224310000689911
116
  }
117
  }
118
  }
@@ -121,34 +267,34 @@
121
  }
122
  },
123
  "UnityEnvironment.step": {
124
- "total": 1.4261614149999673,
125
- "count": 127,
126
  "is_parallel": true,
127
- "self": 0.06783201600018174,
128
  "children": {
129
  "UnityEnvironment._generate_step_input": {
130
- "total": 0.035818923999897834,
131
- "count": 127,
132
  "is_parallel": true,
133
- "self": 0.035818923999897834
134
  },
135
  "communicator.exchange": {
136
- "total": 1.1014211039997122,
137
- "count": 127,
138
  "is_parallel": true,
139
- "self": 1.1014211039997122
140
  },
141
  "steps_from_proto": {
142
- "total": 0.22108937100017556,
143
- "count": 127,
144
  "is_parallel": true,
145
- "self": 0.040240069999356365,
146
  "children": {
147
  "_process_rank_one_or_two_observation": {
148
- "total": 0.1808493010008192,
149
- "count": 1270,
150
  "is_parallel": true,
151
- "self": 0.1808493010008192
152
  }
153
  }
154
  }
@@ -159,31 +305,33 @@
159
  }
160
  }
161
  }
162
- }
163
- }
164
- },
165
- "trainer_threads": {
166
- "total": 3.375100004632259e-05,
167
- "count": 1,
168
- "self": 3.375100004632259e-05,
169
- "children": {
170
- "thread_root": {
171
- "total": 0.0,
172
- "count": 0,
173
- "is_parallel": true,
174
- "self": 0.0,
175
  "children": {
176
- "trainer_advance": {
177
- "total": 2.012712784001053,
178
- "count": 7155,
179
- "is_parallel": true,
180
- "self": 0.08729719900270538,
181
  "children": {
182
- "process_trajectory": {
183
- "total": 1.9254155849983476,
184
- "count": 7155,
185
- "is_parallel": true,
186
- "self": 1.9254155849983476
 
 
 
 
 
 
 
 
 
 
 
187
  }
188
  }
189
  }
@@ -191,15 +339,20 @@
191
  }
192
  }
193
  },
 
 
 
 
 
194
  "TrainerController._save_models": {
195
- "total": 0.002798935000100755,
196
  "count": 1,
197
- "self": 3.2903999908739934e-05,
198
  "children": {
199
  "RLTrainer._checkpoint": {
200
- "total": 0.002766031000192015,
201
  "count": 1,
202
- "self": 0.002766031000192015
203
  }
204
  }
205
  }
 
1
  {
2
  "name": "root",
3
+ "gauges": {
4
+ "SnowballTarget.Policy.Entropy.mean": {
5
+ "value": 0.803484320640564,
6
+ "min": 0.7628971338272095,
7
+ "max": 2.8903205394744873,
8
+ "count": 200
9
+ },
10
+ "SnowballTarget.Policy.Entropy.sum": {
11
+ "value": 565.6529541015625,
12
+ "min": 537.07958984375,
13
+ "max": 4298.21630859375,
14
+ "count": 200
15
+ },
16
+ "SnowballTarget.Step.mean": {
17
+ "value": 199984.0,
18
+ "min": 960.0,
19
+ "max": 199984.0,
20
+ "count": 200
21
+ },
22
+ "SnowballTarget.Step.sum": {
23
+ "value": 199984.0,
24
+ "min": 960.0,
25
+ "max": 199984.0,
26
+ "count": 200
27
+ },
28
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
29
+ "value": 13.181304931640625,
30
+ "min": 0.06443431973457336,
31
+ "max": 13.206515312194824,
32
+ "count": 200
33
+ },
34
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
35
+ "value": 210.90087890625,
36
+ "min": 0.9665148258209229,
37
+ "max": 342.58013916015625,
38
+ "count": 200
39
+ },
40
+ "SnowballTarget.IsTraining.mean": {
41
+ "value": 1.0,
42
+ "min": 1.0,
43
+ "max": 1.0,
44
+ "count": 200
45
+ },
46
+ "SnowballTarget.IsTraining.sum": {
47
+ "value": 1.0,
48
+ "min": 1.0,
49
+ "max": 1.0,
50
+ "count": 200
51
+ },
52
+ "SnowballTarget.Losses.PolicyLoss.mean": {
53
+ "value": 0.07686452096437707,
54
+ "min": 0.0507554501533627,
55
+ "max": 0.09012304773262027,
56
+ "count": 90
57
+ },
58
+ "SnowballTarget.Losses.PolicyLoss.sum": {
59
+ "value": 0.07686452096437707,
60
+ "min": 0.0507554501533627,
61
+ "max": 0.09012304773262027,
62
+ "count": 90
63
+ },
64
+ "SnowballTarget.Losses.ValueLoss.mean": {
65
+ "value": 0.20188107180829143,
66
+ "min": 0.10993161987440259,
67
+ "max": 0.3576154013474782,
68
+ "count": 90
69
+ },
70
+ "SnowballTarget.Losses.ValueLoss.sum": {
71
+ "value": 0.20188107180829143,
72
+ "min": 0.10993161987440259,
73
+ "max": 0.3576154013474782,
74
+ "count": 90
75
+ },
76
+ "SnowballTarget.Policy.LearningRate.mean": {
77
+ "value": 3.1320989560000013e-06,
78
+ "min": 3.1320989560000013e-06,
79
+ "max": 0.000296832001056,
80
+ "count": 90
81
+ },
82
+ "SnowballTarget.Policy.LearningRate.sum": {
83
+ "value": 3.1320989560000013e-06,
84
+ "min": 3.1320989560000013e-06,
85
+ "max": 0.000296832001056,
86
+ "count": 90
87
+ },
88
+ "SnowballTarget.Policy.Epsilon.mean": {
89
+ "value": 0.101044,
90
+ "min": 0.101044,
91
+ "max": 0.198944,
92
+ "count": 90
93
+ },
94
+ "SnowballTarget.Policy.Epsilon.sum": {
95
+ "value": 0.101044,
96
+ "min": 0.101044,
97
+ "max": 0.198944,
98
+ "count": 90
99
+ },
100
+ "SnowballTarget.Policy.Beta.mean": {
101
+ "value": 6.209560000000005e-05,
102
+ "min": 6.209560000000005e-05,
103
+ "max": 0.0049473056,
104
+ "count": 90
105
+ },
106
+ "SnowballTarget.Policy.Beta.sum": {
107
+ "value": 6.209560000000005e-05,
108
+ "min": 6.209560000000005e-05,
109
+ "max": 0.0049473056,
110
+ "count": 90
111
+ },
112
+ "SnowballTarget.Environment.EpisodeLength.mean": {
113
+ "value": 199.0,
114
+ "min": 199.0,
115
+ "max": 199.0,
116
+ "count": 90
117
+ },
118
+ "SnowballTarget.Environment.EpisodeLength.sum": {
119
+ "value": 2189.0,
120
+ "min": 2189.0,
121
+ "max": 2189.0,
122
+ "count": 90
123
+ },
124
+ "SnowballTarget.Environment.CumulativeReward.mean": {
125
+ "value": 29.0,
126
+ "min": 3.0,
127
+ "max": 30.0,
128
+ "count": 108
129
+ },
130
+ "SnowballTarget.Environment.CumulativeReward.sum": {
131
+ "value": 29.0,
132
+ "min": 3.0,
133
+ "max": 296.0,
134
+ "count": 108
135
+ },
136
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
137
+ "value": 29.0,
138
+ "min": 3.0,
139
+ "max": 30.0,
140
+ "count": 108
141
+ },
142
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
143
+ "value": 29.0,
144
+ "min": 3.0,
145
+ "max": 296.0,
146
+ "count": 108
147
+ }
148
+ },
149
  "metadata": {
150
  "timer_format_version": "0.1.0",
151
+ "start_time_seconds": "1736831740",
152
  "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
153
+ "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
154
  "mlagents_version": "1.2.0.dev0",
155
  "mlagents_envs_version": "1.2.0.dev0",
156
  "communication_protocol_version": "1.5.0",
157
  "pytorch_version": "2.5.1+cu121",
158
  "numpy_version": "1.23.5",
159
+ "end_time_seconds": "1736832172"
160
  },
161
+ "total": 431.8959257030001,
162
  "count": 1,
163
+ "self": 0.42808311700082413,
164
  "children": {
165
  "run_training.setup": {
166
+ "total": 0.05584461599983115,
167
  "count": 1,
168
+ "self": 0.05584461599983115
169
  },
170
  "TrainerController.start_learning": {
171
+ "total": 431.41199796999945,
172
  "count": 1,
173
+ "self": 0.3641833590127135,
174
  "children": {
175
  "TrainerController._reset_env": {
176
+ "total": 1.941880212000342,
177
  "count": 1,
178
+ "self": 1.941880212000342
179
  },
180
  "TrainerController.advance": {
181
+ "total": 429.01779893198636,
182
+ "count": 18192,
183
+ "self": 0.37645742895165313,
184
  "children": {
185
  "env_step": {
186
+ "total": 301.3302726129846,
187
+ "count": 18192,
188
+ "self": 230.04266327501045,
189
  "children": {
190
  "SubprocessEnvManager._take_step": {
191
+ "total": 71.06606058199532,
192
+ "count": 18192,
193
+ "self": 1.2500780270042924,
194
  "children": {
195
  "TorchPolicy.evaluate": {
196
+ "total": 69.81598255499102,
197
+ "count": 18192,
198
+ "self": 69.81598255499102
199
  }
200
  }
201
  },
202
  "workers": {
203
+ "total": 0.22154875597880164,
204
+ "count": 18192,
205
  "self": 0.0,
206
  "children": {
207
  "worker_root": {
208
+ "total": 429.78371514798255,
209
+ "count": 18192,
210
  "is_parallel": true,
211
+ "self": 228.42536628699145,
212
  "children": {
213
  "run_training.setup": {
214
  "total": 0.0,
 
217
  "self": 0.0,
218
  "children": {
219
  "steps_from_proto": {
220
+ "total": 0.002265427000111231,
221
  "count": 1,
222
  "is_parallel": true,
223
+ "self": 0.000676131000091118,
224
  "children": {
225
  "_process_rank_one_or_two_observation": {
226
+ "total": 0.0015892960000201128,
227
  "count": 10,
228
  "is_parallel": true,
229
+ "self": 0.0015892960000201128
230
  }
231
  }
232
  },
233
  "UnityEnvironment.step": {
234
+ "total": 0.03557796499990218,
235
  "count": 1,
236
  "is_parallel": true,
237
+ "self": 0.0008088620002126845,
238
  "children": {
239
  "UnityEnvironment._generate_step_input": {
240
+ "total": 0.00039372099990941933,
241
  "count": 1,
242
  "is_parallel": true,
243
+ "self": 0.00039372099990941933
244
  },
245
  "communicator.exchange": {
246
+ "total": 0.03227820199981579,
247
  "count": 1,
248
  "is_parallel": true,
249
+ "self": 0.03227820199981579
250
  },
251
  "steps_from_proto": {
252
+ "total": 0.0020971799999642826,
253
  "count": 1,
254
  "is_parallel": true,
255
+ "self": 0.00042500300014580716,
256
  "children": {
257
  "_process_rank_one_or_two_observation": {
258
+ "total": 0.0016721769998184755,
259
  "count": 10,
260
  "is_parallel": true,
261
+ "self": 0.0016721769998184755
262
  }
263
  }
264
  }
 
267
  }
268
  },
269
  "UnityEnvironment.step": {
270
+ "total": 201.3583488609911,
271
+ "count": 18191,
272
  "is_parallel": true,
273
+ "self": 9.91710704694924,
274
  "children": {
275
  "UnityEnvironment._generate_step_input": {
276
+ "total": 5.416393375051484,
277
+ "count": 18191,
278
  "is_parallel": true,
279
+ "self": 5.416393375051484
280
  },
281
  "communicator.exchange": {
282
+ "total": 153.93211714395966,
283
+ "count": 18191,
284
  "is_parallel": true,
285
+ "self": 153.93211714395966
286
  },
287
  "steps_from_proto": {
288
+ "total": 32.09273129503072,
289
+ "count": 18191,
290
  "is_parallel": true,
291
+ "self": 5.807635553239379,
292
  "children": {
293
  "_process_rank_one_or_two_observation": {
294
+ "total": 26.285095741791338,
295
+ "count": 181910,
296
  "is_parallel": true,
297
+ "self": 26.285095741791338
298
  }
299
  }
300
  }
 
305
  }
306
  }
307
  }
308
+ },
309
+ "trainer_advance": {
310
+ "total": 127.31106889005014,
311
+ "count": 18192,
312
+ "self": 0.4472302320777999,
 
 
 
 
 
 
 
 
313
  "children": {
314
+ "process_trajectory": {
315
+ "total": 29.12317135297417,
316
+ "count": 18192,
317
+ "self": 28.60563932797413,
 
318
  "children": {
319
+ "RLTrainer._checkpoint": {
320
+ "total": 0.5175320250000368,
321
+ "count": 4,
322
+ "self": 0.5175320250000368
323
+ }
324
+ }
325
+ },
326
+ "_update_policy": {
327
+ "total": 97.74066730499817,
328
+ "count": 90,
329
+ "self": 40.48459548499795,
330
+ "children": {
331
+ "TorchPPOOptimizer.update": {
332
+ "total": 57.256071820000216,
333
+ "count": 4587,
334
+ "self": 57.256071820000216
335
  }
336
  }
337
  }
 
339
  }
340
  }
341
  },
342
+ "trainer_threads": {
343
+ "total": 1.0730000212788582e-06,
344
+ "count": 1,
345
+ "self": 1.0730000212788582e-06
346
+ },
347
  "TrainerController._save_models": {
348
+ "total": 0.08813439400000789,
349
  "count": 1,
350
+ "self": 0.0011575770004128572,
351
  "children": {
352
  "RLTrainer._checkpoint": {
353
+ "total": 0.08697681699959503,
354
  "count": 1,
355
+ "self": 0.08697681699959503
356
  }
357
  }
358
  }
run_logs/training_status.json CHANGED
@@ -1,4 +1,62 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "metadata": {
3
  "stats_format_version": "0.3.0",
4
  "mlagents_version": "1.2.0.dev0",
 
1
  {
2
+ "SnowballTarget": {
3
+ "checkpoints": [
4
+ {
5
+ "steps": 49936,
6
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
7
+ "reward": 14.636363636363637,
8
+ "creation_time": 1736831852.111799,
9
+ "auxillary_file_paths": [
10
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
11
+ ]
12
+ },
13
+ {
14
+ "steps": 99960,
15
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
16
+ "reward": 24.363636363636363,
17
+ "creation_time": 1736831958.6092737,
18
+ "auxillary_file_paths": [
19
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
20
+ ]
21
+ },
22
+ {
23
+ "steps": 149984,
24
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
25
+ "reward": 24.818181818181817,
26
+ "creation_time": 1736832066.7548122,
27
+ "auxillary_file_paths": [
28
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
29
+ ]
30
+ },
31
+ {
32
+ "steps": 199984,
33
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
34
+ "reward": 25.636363636363637,
35
+ "creation_time": 1736832172.0954955,
36
+ "auxillary_file_paths": [
37
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
38
+ ]
39
+ },
40
+ {
41
+ "steps": 200112,
42
+ "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
43
+ "reward": 25.636363636363637,
44
+ "creation_time": 1736832172.417992,
45
+ "auxillary_file_paths": [
46
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
47
+ ]
48
+ }
49
+ ],
50
+ "final_checkpoint": {
51
+ "steps": 200112,
52
+ "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
53
+ "reward": 25.636363636363637,
54
+ "creation_time": 1736832172.417992,
55
+ "auxillary_file_paths": [
56
+ "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
57
+ ]
58
+ }
59
+ },
60
  "metadata": {
61
  "stats_format_version": "0.3.0",
62
  "mlagents_version": "1.2.0.dev0",