PraveenKishore's picture
Second Pyramids
0baef17
raw
history blame
19.2 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5548450350761414,
"min": 0.5548450350761414,
"max": 0.9097636938095093,
"count": 17
},
"Pyramids.Policy.Entropy.sum": {
"value": 16538.8203125,
"min": 9048.5341796875,
"max": 27394.8046875,
"count": 17
},
"Pyramids.Step.mean": {
"value": 989877.0,
"min": 509969.0,
"max": 989877.0,
"count": 17
},
"Pyramids.Step.sum": {
"value": 989877.0,
"min": 509969.0,
"max": 989877.0,
"count": 17
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4498426616191864,
"min": 0.018395353108644485,
"max": 0.47865211963653564,
"count": 17
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 121.00767517089844,
"min": 1.471628189086914,
"max": 130.67202758789062,
"count": 17
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.15813587605953217,
"min": -0.15813587605953217,
"max": 0.18717536330223083,
"count": 17
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -42.538551330566406,
"min": -42.538551330566406,
"max": 50.537349700927734,
"count": 17
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06940189483256767,
"min": 0.06384416604364038,
"max": 0.07085341716899786,
"count": 17
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9716265276559474,
"min": 0.21131838193590136,
"max": 1.0338376412298256,
"count": 17
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.02051455678502818,
"min": 0.004671117367647003,
"max": 0.02051455678502818,
"count": 17
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.28720379499039456,
"min": 0.021576496421403135,
"max": 0.28720379499039456,
"count": 17
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.646754593971431e-06,
"min": 7.646754593971431e-06,
"max": 0.0001481200506266667,
"count": 17
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010705456431560002,
"min": 0.00010705456431560002,
"max": 0.0019958326347227,
"count": 17
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254888571428573,
"min": 0.10254888571428573,
"max": 0.14937333333333333,
"count": 17
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356844000000002,
"min": 0.44811999999999996,
"max": 2.0773133,
"count": 17
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002646336828571429,
"min": 0.0002646336828571429,
"max": 0.004942395999999999,
"count": 17
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003704871560000001,
"min": 0.003704871560000001,
"max": 0.06660120227,
"count": 17
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011130442842841148,
"min": 0.011130442842841148,
"max": 0.018592344596982002,
"count": 17
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15582619607448578,
"min": 0.055777035653591156,
"max": 0.25444158911705017,
"count": 17
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 381.958904109589,
"min": 381.958904109589,
"max": 835.3428571428572,
"count": 17
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27883.0,
"min": 2341.0,
"max": 31805.0,
"count": 17
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5632301107661364,
"min": -0.04676927492404596,
"max": 1.5632301107661364,
"count": 17
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 114.11579808592796,
"min": -1.8240017220377922,
"max": 114.88739801198244,
"count": 17
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5632301107661364,
"min": -0.04676927492404596,
"max": 1.5632301107661364,
"count": 17
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 114.11579808592796,
"min": -1.8240017220377922,
"max": 114.88739801198244,
"count": 17
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04380278093405451,
"min": 0.04380278093405451,
"max": 0.15401908088750085,
"count": 17
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.197603008185979,
"min": 0.4970928718103096,
"max": 6.006744154612534,
"count": 17
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 17
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1666820411",
"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 --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": "1666821515"
},
"total": 1104.50703153,
"count": 1,
"self": 0.44053384599965284,
"children": {
"run_training.setup": {
"total": 0.043343765000372514,
"count": 1,
"self": 0.043343765000372514
},
"TrainerController.start_learning": {
"total": 1104.023153919,
"count": 1,
"self": 0.8265517110116889,
"children": {
"TrainerController._reset_env": {
"total": 6.503371287999926,
"count": 1,
"self": 6.503371287999926
},
"TrainerController.advance": {
"total": 1096.5990557029882,
"count": 32026,
"self": 0.8887431339071554,
"children": {
"env_step": {
"total": 734.722037918054,
"count": 32026,
"self": 676.3580663430766,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.92033342601144,
"count": 32026,
"self": 2.486959676054994,
"children": {
"TorchPolicy.evaluate": {
"total": 55.433373749956445,
"count": 31318,
"self": 18.669532147922382,
"children": {
"TorchPolicy.sample_actions": {
"total": 36.76384160203406,
"count": 31318,
"self": 36.76384160203406
}
}
}
}
},
"workers": {
"total": 0.4436381489658743,
"count": 32026,
"self": 0.0,
"children": {
"worker_root": {
"total": 1101.6087957520535,
"count": 32026,
"is_parallel": true,
"self": 481.4929296781247,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019209470001442241,
"count": 1,
"is_parallel": true,
"self": 0.0007091149991538259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012118320009903982,
"count": 8,
"is_parallel": true,
"self": 0.0012118320009903982
}
}
},
"UnityEnvironment.step": {
"total": 0.060161157000038656,
"count": 1,
"is_parallel": true,
"self": 0.0005135700002938393,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004762000003211142,
"count": 1,
"is_parallel": true,
"self": 0.0004762000003211142
},
"communicator.exchange": {
"total": 0.05752015199959715,
"count": 1,
"is_parallel": true,
"self": 0.05752015199959715
},
"steps_from_proto": {
"total": 0.0016512349998265563,
"count": 1,
"is_parallel": true,
"self": 0.000425104999976611,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012261299998499453,
"count": 8,
"is_parallel": true,
"self": 0.0012261299998499453
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 620.1158660739288,
"count": 32025,
"is_parallel": true,
"self": 14.729850475844614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.183287286025916,
"count": 32025,
"is_parallel": true,
"self": 12.183287286025916
},
"communicator.exchange": {
"total": 545.050911685014,
"count": 32025,
"is_parallel": true,
"self": 545.050911685014
},
"steps_from_proto": {
"total": 48.151816627044354,
"count": 32025,
"is_parallel": true,
"self": 12.507719423942035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.64409720310232,
"count": 256200,
"is_parallel": true,
"self": 35.64409720310232
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 360.98827465102704,
"count": 32026,
"self": 1.5785568430037529,
"children": {
"process_trajectory": {
"total": 82.8166930020293,
"count": 32026,
"self": 82.70609321602933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11059978599996612,
"count": 1,
"self": 0.11059978599996612
}
}
},
"_update_policy": {
"total": 276.593024805994,
"count": 234,
"self": 109.23629919799805,
"children": {
"TorchPPOOptimizer.update": {
"total": 167.35672560799594,
"count": 11340,
"self": 167.35672560799594
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.244000031874748e-06,
"count": 1,
"self": 1.244000031874748e-06
},
"TrainerController._save_models": {
"total": 0.09417397300012453,
"count": 1,
"self": 0.002133608999884018,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09204036400024052,
"count": 1,
"self": 0.09204036400024052
}
}
}
}
}
}
}