ppo-Pyramids / run_logs /timers.json
Schoolar's picture
pyramids_1
db8141c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.388824999332428,
"min": 0.388824999332428,
"max": 1.438249111175537,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11689.634765625,
"min": 11689.634765625,
"max": 43630.7265625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989969.0,
"min": 29952.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989969.0,
"min": 29952.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.555325984954834,
"min": -0.14623549580574036,
"max": 0.5786536931991577,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 154.93594360351562,
"min": -35.096519470214844,
"max": 163.1803436279297,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.006510900799185038,
"min": -0.023791857063770294,
"max": 0.38197392225265503,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.816541314125061,
"min": -6.542760848999023,
"max": 90.52781677246094,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06663551857546285,
"min": 0.0650911313146242,
"max": 0.07411157513175226,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9328972600564799,
"min": 0.4728711173304654,
"max": 1.1035955797757624,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015025767552461253,
"min": 0.0012478948109276853,
"max": 0.015025767552461253,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21036074573445754,
"min": 0.013726842920204539,
"max": 0.21036074573445754,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.619047460350002e-06,
"min": 7.619047460350002e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010666666444490002,
"min": 0.00010666666444490002,
"max": 0.0036329923890025995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253965,
"min": 0.10253965,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355551,
"min": 1.3886848,
"max": 2.6109974,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002637110350000001,
"min": 0.0002637110350000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036919544900000014,
"min": 0.0036919544900000014,
"max": 0.12111864026,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008004260249435902,
"min": 0.008004260249435902,
"max": 0.4655895233154297,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11205964535474777,
"min": 0.11205964535474777,
"max": 3.259126663208008,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 322.20652173913044,
"min": 322.20652173913044,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29643.0,
"min": 15984.0,
"max": 33084.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.612552153189545,
"min": -1.0000000521540642,
"max": 1.612552153189545,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 148.35479809343815,
"min": -29.894001699984074,
"max": 148.35479809343815,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.612552153189545,
"min": -1.0000000521540642,
"max": 1.612552153189545,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 148.35479809343815,
"min": -29.894001699984074,
"max": 148.35479809343815,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.026542695238237247,
"min": 0.026542695238237247,
"max": 9.452214850112796,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.441927961917827,
"min": 2.441927961917827,
"max": 151.23543760180473,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677433376",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677435608"
},
"total": 2231.436001924,
"count": 1,
"self": 1.0583671429999413,
"children": {
"run_training.setup": {
"total": 0.1053833510000004,
"count": 1,
"self": 0.1053833510000004
},
"TrainerController.start_learning": {
"total": 2230.27225143,
"count": 1,
"self": 1.3897577580187317,
"children": {
"TrainerController._reset_env": {
"total": 7.074438240999825,
"count": 1,
"self": 7.074438240999825
},
"TrainerController.advance": {
"total": 2221.6770735879813,
"count": 63953,
"self": 1.4501231359326994,
"children": {
"env_step": {
"total": 1492.9290788389844,
"count": 63953,
"self": 1376.9265394699082,
"children": {
"SubprocessEnvManager._take_step": {
"total": 115.13365321800666,
"count": 63953,
"self": 4.919489838971913,
"children": {
"TorchPolicy.evaluate": {
"total": 110.21416337903474,
"count": 62561,
"self": 37.109446960037076,
"children": {
"TorchPolicy.sample_actions": {
"total": 73.10471641899767,
"count": 62561,
"self": 73.10471641899767
}
}
}
}
},
"workers": {
"total": 0.868886151069546,
"count": 63953,
"self": 0.0,
"children": {
"worker_root": {
"total": 2225.0124128829607,
"count": 63953,
"is_parallel": true,
"self": 967.495096819996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025156990000141377,
"count": 1,
"is_parallel": true,
"self": 0.0008818639994387922,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016338350005753455,
"count": 8,
"is_parallel": true,
"self": 0.0016338350005753455
}
}
},
"UnityEnvironment.step": {
"total": 0.046798672000022634,
"count": 1,
"is_parallel": true,
"self": 0.0005608500000562344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004820320000362699,
"count": 1,
"is_parallel": true,
"self": 0.0004820320000362699
},
"communicator.exchange": {
"total": 0.0441590659997928,
"count": 1,
"is_parallel": true,
"self": 0.0441590659997928
},
"steps_from_proto": {
"total": 0.0015967240001373284,
"count": 1,
"is_parallel": true,
"self": 0.0004351879997557262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011615360003816022,
"count": 8,
"is_parallel": true,
"self": 0.0011615360003816022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1257.5173160629647,
"count": 63952,
"is_parallel": true,
"self": 31.09917037277137,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.862513622085316,
"count": 63952,
"is_parallel": true,
"self": 23.862513622085316
},
"communicator.exchange": {
"total": 1107.6259554370613,
"count": 63952,
"is_parallel": true,
"self": 1107.6259554370613
},
"steps_from_proto": {
"total": 94.92967663104673,
"count": 63952,
"is_parallel": true,
"self": 23.176241564139673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.75343506690706,
"count": 511616,
"is_parallel": true,
"self": 71.75343506690706
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 727.2978716130642,
"count": 63953,
"self": 2.802836641047179,
"children": {
"process_trajectory": {
"total": 165.9586613300212,
"count": 63953,
"self": 165.72764803102064,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23101329900055134,
"count": 2,
"self": 0.23101329900055134
}
}
},
"_update_policy": {
"total": 558.5363736419959,
"count": 452,
"self": 216.92354431395688,
"children": {
"TorchPPOOptimizer.update": {
"total": 341.61282932803897,
"count": 22818,
"self": 341.61282932803897
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.225999767484609e-06,
"count": 1,
"self": 1.225999767484609e-06
},
"TrainerController._save_models": {
"total": 0.1309806170002048,
"count": 1,
"self": 0.0019767570001931745,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12900386000001163,
"count": 1,
"self": 0.12900386000001163
}
}
}
}
}
}
}