|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.9041121602058411, |
|
"min": 0.7848484516143799, |
|
"max": 0.9595794677734375, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 27195.693359375, |
|
"min": 11791.3125, |
|
"max": 27195.693359375, |
|
"count": 9 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479893.0, |
|
"min": 239887.0, |
|
"max": 479893.0, |
|
"count": 9 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479893.0, |
|
"min": 239887.0, |
|
"max": 479893.0, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.04746060445904732, |
|
"min": -0.09365838766098022, |
|
"max": -0.04746060445904732, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -11.485466003417969, |
|
"min": -22.32797622680664, |
|
"max": -8.710229873657227, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.023278461769223213, |
|
"min": 0.02264345809817314, |
|
"max": 0.05445399507880211, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.633387565612793, |
|
"min": 5.055502891540527, |
|
"max": 13.232320785522461, |
|
"count": 9 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06821797406222639, |
|
"min": 0.06606155096887942, |
|
"max": 0.07089489593326456, |
|
"count": 9 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9550516368711696, |
|
"min": 0.13847115474345628, |
|
"max": 1.0298248680214874, |
|
"count": 9 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.003247611720624019, |
|
"min": 6.513744602898441e-05, |
|
"max": 0.004006296664693746, |
|
"count": 9 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.04546656408873626, |
|
"min": 0.00013027489205796883, |
|
"max": 0.06009444997040618, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.0508521735285716e-05, |
|
"min": 2.0508521735285716e-05, |
|
"max": 0.00015952384682539996, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.000287119304294, |
|
"min": 0.000287119304294, |
|
"max": 0.0016115711628098, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10683614285714285, |
|
"min": 0.10683614285714285, |
|
"max": 0.15317460000000002, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.495706, |
|
"min": 0.30634920000000004, |
|
"max": 1.9182626000000003, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0006929306714285714, |
|
"min": 0.0006929306714285714, |
|
"max": 0.005322142540000001, |
|
"count": 9 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0097010294, |
|
"min": 0.0097010294, |
|
"max": 0.053775300979999996, |
|
"count": 9 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.02004416659474373, |
|
"min": 0.02004416659474373, |
|
"max": 0.03485111892223358, |
|
"count": 9 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2806183397769928, |
|
"min": 0.06968533247709274, |
|
"max": 0.41131991147994995, |
|
"count": 9 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 9 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 9 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 936.969696969697, |
|
"min": 879.7096774193549, |
|
"max": 972.71875, |
|
"count": 8 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30920.0, |
|
"min": 27271.0, |
|
"max": 33147.0, |
|
"count": 8 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.5130727715564497, |
|
"min": -0.8450303508928327, |
|
"max": -0.23489036050535017, |
|
"count": 8 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -16.93140146136284, |
|
"min": -27.886001579463482, |
|
"max": -7.281601175665855, |
|
"count": 8 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.5130727715564497, |
|
"min": -0.8450303508928327, |
|
"max": -0.23489036050535017, |
|
"count": 8 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -16.93140146136284, |
|
"min": -27.886001579463482, |
|
"max": -7.281601175665855, |
|
"count": 8 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.19533019177051206, |
|
"min": 0.19521545268775475, |
|
"max": 0.3576231829144738, |
|
"count": 8 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.4458963284268975, |
|
"min": 6.051679033320397, |
|
"max": 11.801565036177635, |
|
"count": 8 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1661327764", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \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 --resume", |
|
"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": "1661328295" |
|
}, |
|
"total": 531.3314669409999, |
|
"count": 1, |
|
"self": 0.47608576500010713, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04129923999994389, |
|
"count": 1, |
|
"self": 0.04129923999994389 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 530.8140819359999, |
|
"count": 1, |
|
"self": 0.36486737998234275, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.394633533999922, |
|
"count": 1, |
|
"self": 6.394633533999922 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 523.9569498660176, |
|
"count": 17254, |
|
"self": 0.3886675750225095, |
|
"children": { |
|
"env_step": { |
|
"total": 326.518640019995, |
|
"count": 17254, |
|
"self": 296.9802634349719, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 29.342362959018146, |
|
"count": 17254, |
|
"self": 1.2719700340148847, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 28.07039292500326, |
|
"count": 17066, |
|
"self": 9.626990931975115, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 18.443401993028147, |
|
"count": 17066, |
|
"self": 18.443401993028147 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.1960136260049694, |
|
"count": 17254, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 529.4455741930317, |
|
"count": 17254, |
|
"is_parallel": true, |
|
"self": 259.8603227820204, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001969468000197594, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007206939999377937, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012487740002598002, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012487740002598002 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0783110890001808, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005022090003876656, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004492939999636292, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004492939999636292 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07567265499983478, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07567265499983478 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001686930999994729, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046135300021887815, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001225577999775851, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001225577999775851 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 269.5852514110113, |
|
"count": 17253, |
|
"is_parallel": true, |
|
"self": 7.47424173697209, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 6.2597261700022955, |
|
"count": 17253, |
|
"is_parallel": true, |
|
"self": 6.2597261700022955 |
|
}, |
|
"communicator.exchange": { |
|
"total": 230.8160746030187, |
|
"count": 17253, |
|
"is_parallel": true, |
|
"self": 230.8160746030187 |
|
}, |
|
"steps_from_proto": { |
|
"total": 25.035208901018223, |
|
"count": 17253, |
|
"is_parallel": true, |
|
"self": 6.137271586999304, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 18.897937314018918, |
|
"count": 138024, |
|
"is_parallel": true, |
|
"self": 18.897937314018918 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 197.04964227100004, |
|
"count": 17254, |
|
"self": 0.6649830680039486, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 44.51095304099567, |
|
"count": 17254, |
|
"self": 44.27786605799565, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.23308698300002106, |
|
"count": 1, |
|
"self": 0.23308698300002106 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 151.87370616200042, |
|
"count": 118, |
|
"self": 59.55791987000248, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 92.31578629199794, |
|
"count": 6192, |
|
"self": 92.31578629199794 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1750000794563675e-06, |
|
"count": 1, |
|
"self": 1.1750000794563675e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09762998099995457, |
|
"count": 1, |
|
"self": 0.0019720509999388014, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09565793000001577, |
|
"count": 1, |
|
"self": 0.09565793000001577 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |