|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7619636058807373, |
|
"min": 0.7583403587341309, |
|
"max": 1.4529799222946167, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 22883.291015625, |
|
"min": 22738.078125, |
|
"max": 44077.59765625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479993.0, |
|
"min": 29998.0, |
|
"max": 479993.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479993.0, |
|
"min": 29998.0, |
|
"max": 479993.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.22424274682998657, |
|
"min": -0.09909290820360184, |
|
"max": 0.2695452570915222, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 57.18190002441406, |
|
"min": -23.881391525268555, |
|
"max": 70.0817642211914, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.09483246505260468, |
|
"min": -0.20641285181045532, |
|
"max": 0.37465405464172363, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -24.18227767944336, |
|
"min": -53.66734313964844, |
|
"max": 89.16766357421875, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06948464471994865, |
|
"min": 0.06498117232972929, |
|
"max": 0.07465554425527882, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9727850260792811, |
|
"min": 0.5198493786378343, |
|
"max": 1.1198331638291823, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01197325436594899, |
|
"min": 0.000539064126861868, |
|
"max": 0.016541159630703205, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.16762556112328586, |
|
"min": 0.007546897776066152, |
|
"max": 0.23157623482984488, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.0992378716857135e-05, |
|
"min": 2.0992378716857135e-05, |
|
"max": 0.00028952910349029995, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0002938933020359999, |
|
"min": 0.0002938933020359999, |
|
"max": 0.0032751763082745993, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10699742857142858, |
|
"min": 0.10699742857142858, |
|
"max": 0.1965097, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.497964, |
|
"min": 1.497964, |
|
"max": 2.4222623999999997, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007090431142857142, |
|
"min": 0.0007090431142857142, |
|
"max": 0.00965131903, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009926603599999998, |
|
"min": 0.009926603599999998, |
|
"max": 0.10918336746, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.017906898632645607, |
|
"min": 0.017906898632645607, |
|
"max": 0.40150848031044006, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2506965696811676, |
|
"min": 0.2506965696811676, |
|
"max": 3.2120678424835205, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 642.3541666666666, |
|
"min": 586.5833333333334, |
|
"max": 990.875, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30833.0, |
|
"min": 17180.0, |
|
"max": 33020.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.8992083050931493, |
|
"min": -0.9224968266583258, |
|
"max": 0.9549333057366312, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 43.16199864447117, |
|
"min": -28.5974016264081, |
|
"max": 45.836798675358295, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.8992083050931493, |
|
"min": -0.9224968266583258, |
|
"max": 0.9549333057366312, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 43.16199864447117, |
|
"min": -28.5974016264081, |
|
"max": 45.836798675358295, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.12007196391035298, |
|
"min": 0.10936963379693528, |
|
"max": 7.435492703484164, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.763454267696943, |
|
"min": 5.2497424222528934, |
|
"max": 133.83886866271496, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1666439528", |
|
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1666440562" |
|
}, |
|
"total": 1034.431290364, |
|
"count": 1, |
|
"self": 0.4216097979999631, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04465677799998957, |
|
"count": 1, |
|
"self": 0.04465677799998957 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1033.965023788, |
|
"count": 1, |
|
"self": 0.6742994580301911, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 8.645330374000025, |
|
"count": 1, |
|
"self": 8.645330374000025 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1024.54756339997, |
|
"count": 31718, |
|
"self": 0.7413505300035013, |
|
"children": { |
|
"env_step": { |
|
"total": 667.3003434510024, |
|
"count": 31718, |
|
"self": 613.210570787988, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 53.72077435401644, |
|
"count": 31718, |
|
"self": 2.2775752889802447, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 51.4431990650362, |
|
"count": 31318, |
|
"self": 17.791352517043777, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 33.65184654799242, |
|
"count": 31318, |
|
"self": 33.65184654799242 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.368998308998016, |
|
"count": 31718, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1031.7056363480012, |
|
"count": 31718, |
|
"is_parallel": true, |
|
"self": 470.22869299999763, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005809920999979568, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004543759999933172, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012661610000463952, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012661610000463952 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04682983999998669, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005219219999617053, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00046007700001382545, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046007700001382545 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04432813799996893, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04432813799996893 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015197030000422274, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003962309999678837, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011234720000743437, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011234720000743437 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 561.4769433480036, |
|
"count": 31717, |
|
"is_parallel": true, |
|
"self": 14.250386385994261, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.851275887996223, |
|
"count": 31717, |
|
"is_parallel": true, |
|
"self": 11.851275887996223 |
|
}, |
|
"communicator.exchange": { |
|
"total": 488.72235740901004, |
|
"count": 31717, |
|
"is_parallel": true, |
|
"self": 488.72235740901004 |
|
}, |
|
"steps_from_proto": { |
|
"total": 46.65292366500307, |
|
"count": 31717, |
|
"is_parallel": true, |
|
"self": 11.693720071031862, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 34.95920359397121, |
|
"count": 253736, |
|
"is_parallel": true, |
|
"self": 34.95920359397121 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 356.505869418964, |
|
"count": 31718, |
|
"self": 1.215105115990582, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 80.40730620797427, |
|
"count": 31718, |
|
"self": 80.2935876289742, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11371857900007853, |
|
"count": 1, |
|
"self": 0.11371857900007853 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 274.8834580949991, |
|
"count": 223, |
|
"self": 108.7744983650058, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 166.10895972999333, |
|
"count": 11412, |
|
"self": 166.10895972999333 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1580000318645034e-06, |
|
"count": 1, |
|
"self": 1.1580000318645034e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09782939799993073, |
|
"count": 1, |
|
"self": 0.001673731999744632, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0961556660001861, |
|
"count": 1, |
|
"self": 0.0961556660001861 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |