ppo-PyramidsRND / run_logs /timers.json
feratur's picture
First Push
847a934
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5013000965118408,
"min": 0.49758198857307434,
"max": 1.5428580045700073,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15063.0654296875,
"min": 14919.498046875,
"max": 46804.140625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989996.0,
"min": 29952.0,
"max": 989996.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989996.0,
"min": 29952.0,
"max": 989996.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6224948167800903,
"min": -0.18086323142051697,
"max": 0.6224948167800903,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 176.7885284423828,
"min": -42.864585876464844,
"max": 177.48500061035156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009396024979650974,
"min": -0.016869938001036644,
"max": 0.19009281694889069,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.668471097946167,
"min": -4.656103134155273,
"max": 45.81237030029297,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06686375547679473,
"min": 0.06595325208851462,
"max": 0.07334014145056267,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9360925766751261,
"min": 0.4933091680631015,
"max": 1.0585511313402094,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016142280097559737,
"min": 0.001629780328812312,
"max": 0.01766791480379955,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2259919213658363,
"min": 0.015526996705265559,
"max": 0.2473508072531937,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.702061718392853e-06,
"min": 7.702061718392853e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010782886405749993,
"min": 0.00010782886405749993,
"max": 0.0034925359358214,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256732142857142,
"min": 0.10256732142857142,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359425,
"min": 1.3886848,
"max": 2.5266377,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026647541071428556,
"min": 0.00026647541071428556,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037306557499999977,
"min": 0.0037306557499999977,
"max": 0.11643144214,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009302101098001003,
"min": 0.009302101098001003,
"max": 0.30191999673843384,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1302294135093689,
"min": 0.1302294135093689,
"max": 2.1134400367736816,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 294.62,
"min": 294.62,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29462.0,
"min": 15984.0,
"max": 33737.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.643690895552587,
"min": -1.0000000521540642,
"max": 1.677759169924016,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 162.72539865970612,
"min": -30.44100172817707,
"max": 165.58119855821133,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.643690895552587,
"min": -1.0000000521540642,
"max": 1.677759169924016,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 162.72539865970612,
"min": -30.44100172817707,
"max": 165.58119855821133,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.028417492524668988,
"min": 0.028417492524668988,
"max": 6.08793633710593,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.81333175994223,
"min": 2.81333175994223,
"max": 97.40698139369488,
"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": "1680122572",
"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=Pyramids1 --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": "1680124717"
},
"total": 2145.076427572,
"count": 1,
"self": 1.3467791290004243,
"children": {
"run_training.setup": {
"total": 0.11090908300002411,
"count": 1,
"self": 0.11090908300002411
},
"TrainerController.start_learning": {
"total": 2143.6187393599994,
"count": 1,
"self": 1.3301483020745763,
"children": {
"TrainerController._reset_env": {
"total": 7.072686586000145,
"count": 1,
"self": 7.072686586000145
},
"TrainerController.advance": {
"total": 2135.075550918925,
"count": 63936,
"self": 1.3474983888254428,
"children": {
"env_step": {
"total": 1530.3254891600945,
"count": 63936,
"self": 1424.003131483098,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.51901877393948,
"count": 63936,
"self": 4.559336082879327,
"children": {
"TorchPolicy.evaluate": {
"total": 100.95968269106015,
"count": 62563,
"self": 100.95968269106015
}
}
},
"workers": {
"total": 0.8033389030570106,
"count": 63936,
"self": 0.0,
"children": {
"worker_root": {
"total": 2138.8750381090026,
"count": 63936,
"is_parallel": true,
"self": 828.7370882810874,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001911545999973896,
"count": 1,
"is_parallel": true,
"self": 0.0005749089991695655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013366370008043305,
"count": 8,
"is_parallel": true,
"self": 0.0013366370008043305
}
}
},
"UnityEnvironment.step": {
"total": 0.045370616000127484,
"count": 1,
"is_parallel": true,
"self": 0.0005032929998378677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045581200038213865,
"count": 1,
"is_parallel": true,
"self": 0.00045581200038213865
},
"communicator.exchange": {
"total": 0.042722139000034076,
"count": 1,
"is_parallel": true,
"self": 0.042722139000034076
},
"steps_from_proto": {
"total": 0.0016893719998734014,
"count": 1,
"is_parallel": true,
"self": 0.00037207300010777544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001317298999765626,
"count": 8,
"is_parallel": true,
"self": 0.001317298999765626
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1310.1379498279152,
"count": 63935,
"is_parallel": true,
"self": 30.74546772202848,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.177927434990124,
"count": 63935,
"is_parallel": true,
"self": 22.177927434990124
},
"communicator.exchange": {
"total": 1167.5423349230064,
"count": 63935,
"is_parallel": true,
"self": 1167.5423349230064
},
"steps_from_proto": {
"total": 89.67221974789027,
"count": 63935,
"is_parallel": true,
"self": 18.899994557994432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 70.77222518989583,
"count": 511480,
"is_parallel": true,
"self": 70.77222518989583
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 603.4025633700048,
"count": 63936,
"self": 2.6175861890014858,
"children": {
"process_trajectory": {
"total": 114.62437081799953,
"count": 63936,
"self": 114.38034620399912,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2440246140004092,
"count": 2,
"self": 0.2440246140004092
}
}
},
"_update_policy": {
"total": 486.1606063630038,
"count": 452,
"self": 308.09472255100263,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.06588381200118,
"count": 22740,
"self": 178.06588381200118
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3540002328227274e-06,
"count": 1,
"self": 1.3540002328227274e-06
},
"TrainerController._save_models": {
"total": 0.14035219899960794,
"count": 1,
"self": 0.0020099959992876393,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1383422030003203,
"count": 1,
"self": 0.1383422030003203
}
}
}
}
}
}
}