{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1541626751422882, "min": 0.13893947005271912, "max": 1.4570552110671997, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4592.814453125, "min": 4154.845703125, "max": 44201.2265625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999897.0, "min": 29952.0, "max": 2999897.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999897.0, "min": 29952.0, "max": 2999897.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8661494255065918, "min": -0.10531827062368393, "max": 0.9053352475166321, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 261.5771179199219, "min": -25.381702423095703, "max": 281.55926513671875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004579018801450729, "min": -0.06233183667063713, "max": 0.4041304886341095, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3828636407852173, "min": -16.20627784729004, "max": 95.77892303466797, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06689716793803706, "min": 0.06383060189823264, "max": 0.07369915470605648, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.003457519070556, "min": 0.495744323379684, "max": 1.096912146487739, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015656363462201426, "min": 0.0015655259762150085, "max": 0.016371263852869605, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23484545193302137, "min": 0.017220785738365094, "max": 0.2363000395068643, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5004328332222168e-06, "min": 1.5004328332222168e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.250649249833325e-05, "min": 2.250649249833325e-05, "max": 0.0040111725629425, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050011111111111, "min": 0.10050011111111111, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075016666666667, "min": 1.3962282666666668, "max": 2.812434766666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9961099999999835e-05, "min": 5.9961099999999835e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008994164999999976, "min": 0.0008994164999999976, "max": 0.13371204425, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007728728000074625, "min": 0.007458213716745377, "max": 0.4749503433704376, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11593092232942581, "min": 0.10441499203443527, "max": 3.3246524333953857, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 214.27777777777777, "min": 200.95364238410596, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30856.0, "min": 15984.0, "max": 32843.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7579416533311207, "min": -1.0000000521540642, "max": 1.7990463423413157, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 253.1435980796814, "min": -29.936001621186733, "max": 271.65599769353867, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7579416533311207, "min": -1.0000000521540642, "max": 1.7990463423413157, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 253.1435980796814, "min": -29.936001621186733, "max": 271.65599769353867, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0171737738711373, "min": 0.016029845921191936, "max": 9.576881784945726, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4730234374437714, "min": 2.2155290608352516, "max": 153.23010855913162, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679452907", "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", "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": "1679458433" }, "total": 5525.555571278, "count": 1, "self": 0.3755662539997502, "children": { "run_training.setup": { "total": 0.10648646599975109, "count": 1, "self": 0.10648646599975109 }, "TrainerController.start_learning": { "total": 5525.073518558, "count": 1, "self": 4.05962812011785, "children": { "TrainerController._reset_env": { "total": 6.143234971999846, "count": 1, "self": 6.143234971999846 }, "TrainerController.advance": { "total": 5514.778339930882, "count": 195643, "self": 4.434448521205013, "children": { "env_step": { "total": 3823.8715055957427, "count": 195643, "self": 3520.403688449815, "children": { "SubprocessEnvManager._take_step": { "total": 301.015671197094, "count": 195643, "self": 13.042896849012322, "children": { "TorchPolicy.evaluate": { "total": 287.97277434808166, "count": 187541, "self": 287.97277434808166 } } }, "workers": { "total": 2.4521459488337314, "count": 195643, "self": 0.0, "children": { "worker_root": { "total": 5517.0194389689195, "count": 195643, "is_parallel": true, "self": 2288.573292215909, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018028210001830303, "count": 1, "is_parallel": true, "self": 0.0005932079998274276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012096130003556027, "count": 8, "is_parallel": true, "self": 0.0012096130003556027 } } }, "UnityEnvironment.step": { "total": 0.040432568000142055, "count": 1, "is_parallel": true, "self": 0.00032317199975295807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004736740002044826, "count": 1, "is_parallel": true, "self": 0.0004736740002044826 }, "communicator.exchange": { "total": 0.038555008999992424, "count": 1, "is_parallel": true, "self": 0.038555008999992424 }, "steps_from_proto": { "total": 0.0010807130001921905, "count": 1, "is_parallel": true, "self": 0.0002340149999326968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008466980002594937, "count": 8, "is_parallel": true, "self": 0.0008466980002594937 } } } } } } }, "UnityEnvironment.step": { "total": 3228.4461467530105, "count": 195642, "is_parallel": true, "self": 68.18528253210889, "children": { "UnityEnvironment._generate_step_input": { "total": 49.94051457991873, "count": 195642, "is_parallel": true, "self": 49.94051457991873 }, "communicator.exchange": { "total": 2912.2961945309503, "count": 195642, "is_parallel": true, "self": 2912.2961945309503 }, "steps_from_proto": { "total": 198.02415511003255, "count": 195642, "is_parallel": true, "self": 43.617304850409255, "children": { "_process_rank_one_or_two_observation": { "total": 154.4068502596233, "count": 1565136, "is_parallel": true, "self": 154.4068502596233 } } } } } } } } } } }, "trainer_advance": { "total": 1686.4723858139346, "count": 195643, "self": 7.851833343915587, "children": { "process_trajectory": { "total": 327.704315101033, "count": 195643, "self": 327.1187444330317, "children": { "RLTrainer._checkpoint": { "total": 0.58557066800131, "count": 6, "self": 0.58557066800131 } } }, "_update_policy": { "total": 1350.916237368986, "count": 1398, "self": 840.488502582914, "children": { "TorchPPOOptimizer.update": { "total": 510.42773478607205, "count": 68400, "self": 510.42773478607205 } } } } } } }, "trainer_threads": { "total": 1.0430003385408781e-06, "count": 1, "self": 1.0430003385408781e-06 }, "TrainerController._save_models": { "total": 0.0923144919997867, "count": 1, "self": 0.0015209139992293785, "children": { "RLTrainer._checkpoint": { "total": 0.09079357800055732, "count": 1, "self": 0.09079357800055732 } } } } } } }