|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7264034152030945, |
|
"min": 0.7264034152030945, |
|
"max": 1.39326012134552, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 21792.1015625, |
|
"min": 21792.1015625, |
|
"max": 42265.9375, |
|
"count": 20 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 599928.0, |
|
"min": 29934.0, |
|
"max": 599928.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 599928.0, |
|
"min": 29934.0, |
|
"max": 599928.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.06528972834348679, |
|
"min": -0.12684696912765503, |
|
"max": 0.04935003072023392, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -15.734825134277344, |
|
"min": -30.69696807861328, |
|
"max": 11.69595718383789, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.02683452144265175, |
|
"min": 0.024899248033761978, |
|
"max": 0.38445404171943665, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 6.4671196937561035, |
|
"min": 6.0505170822143555, |
|
"max": 91.11560821533203, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06685126404253035, |
|
"min": 0.06605550085930692, |
|
"max": 0.07388696606302408, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9359176965954249, |
|
"min": 0.5593080437060705, |
|
"max": 1.0177985545842425, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0017227440001490668, |
|
"min": 0.00013530156250678017, |
|
"max": 0.00818283312639278, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.024118416002086935, |
|
"min": 0.0017589203125881422, |
|
"max": 0.06546266501114224, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.810918824964286e-06, |
|
"min": 7.810918824964286e-06, |
|
"max": 0.0002914033778655417, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001093528635495, |
|
"min": 0.0001093528635495, |
|
"max": 0.003220203226599, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10260360714285714, |
|
"min": 0.10260360714285714, |
|
"max": 0.19713445833333332, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4364505, |
|
"min": 1.4364505, |
|
"max": 2.4154093333333333, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002701003535714286, |
|
"min": 0.0002701003535714286, |
|
"max": 0.0097137323875, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037814049500000005, |
|
"min": 0.0037814049500000005, |
|
"max": 0.10736275990000001, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.024200284853577614, |
|
"min": 0.023663345724344254, |
|
"max": 0.4497588872909546, |
|
"count": 20 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.3388039767742157, |
|
"min": 0.33128684759140015, |
|
"max": 3.5980710983276367, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 951.96875, |
|
"min": 880.0322580645161, |
|
"max": 999.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30463.0, |
|
"min": 16477.0, |
|
"max": 32791.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.7722970202113643, |
|
"min": -0.9998645686334179, |
|
"max": -0.3399750445969403, |
|
"count": 20 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -25.48580166697502, |
|
"min": -31.995601683855057, |
|
"max": -10.298801362514496, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.7722970202113643, |
|
"min": -0.9998645686334179, |
|
"max": -0.3399750445969403, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -25.48580166697502, |
|
"min": -31.995601683855057, |
|
"max": -10.298801362514496, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.23994946668884068, |
|
"min": 0.22095727150638897, |
|
"max": 8.74001516138806, |
|
"count": 20 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.918332400731742, |
|
"min": 6.6287181451916695, |
|
"max": 148.58025774359703, |
|
"count": 20 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 20 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1671755755", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \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 --force", |
|
"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": "1671756879" |
|
}, |
|
"total": 1123.716301706, |
|
"count": 1, |
|
"self": 0.4402867050000623, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11121471499996005, |
|
"count": 1, |
|
"self": 0.11121471499996005 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1123.164800286, |
|
"count": 1, |
|
"self": 0.6929341329941963, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.356815223999945, |
|
"count": 1, |
|
"self": 6.356815223999945 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1116.0187025150058, |
|
"count": 37862, |
|
"self": 0.7128574490050141, |
|
"children": { |
|
"env_step": { |
|
"total": 721.7313338440193, |
|
"count": 37862, |
|
"self": 661.708828562025, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 59.58505496199609, |
|
"count": 37862, |
|
"self": 2.480331739991186, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 57.10472322200491, |
|
"count": 37575, |
|
"self": 19.2368949170085, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 37.86782830499641, |
|
"count": 37575, |
|
"self": 37.86782830499641 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.43745031999822004, |
|
"count": 37862, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1120.964816913992, |
|
"count": 37862, |
|
"is_parallel": true, |
|
"self": 515.6972927339953, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019799600000283135, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00073862500011046, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012413349999178536, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012413349999178536 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.059374694999974054, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006325979999246556, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00043444499999623076, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043444499999623076 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.056609270000024026, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.056609270000024026 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016983820000291416, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045654800010197505, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012418339999271666, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012418339999271666 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 605.2675241799968, |
|
"count": 37861, |
|
"is_parallel": true, |
|
"self": 16.618981516984377, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 13.836642041995503, |
|
"count": 37861, |
|
"is_parallel": true, |
|
"self": 13.836642041995503 |
|
}, |
|
"communicator.exchange": { |
|
"total": 520.210887300002, |
|
"count": 37861, |
|
"is_parallel": true, |
|
"self": 520.210887300002 |
|
}, |
|
"steps_from_proto": { |
|
"total": 54.601013321015046, |
|
"count": 37861, |
|
"is_parallel": true, |
|
"self": 12.556083768983854, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 42.04492955203119, |
|
"count": 302888, |
|
"is_parallel": true, |
|
"self": 42.04492955203119 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 393.5745112219815, |
|
"count": 37862, |
|
"self": 1.1478582319853672, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 84.49854577399759, |
|
"count": 37862, |
|
"self": 84.38307914699766, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11546662699993249, |
|
"count": 1, |
|
"self": 0.11546662699993249 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 307.9281072159985, |
|
"count": 259, |
|
"self": 119.28937673300129, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 188.63873048299723, |
|
"count": 13734, |
|
"self": 188.63873048299723 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.030000001075678e-07, |
|
"count": 1, |
|
"self": 9.030000001075678e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0963475109999763, |
|
"count": 1, |
|
"self": 0.0019020790000467969, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0944454319999295, |
|
"count": 1, |
|
"self": 0.0944454319999295 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |