ppo-PyramidsRND / run_logs /timers.json
vitorhgomes's picture
hey yo
0a85853
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.37493664026260376,
"min": 0.37493664026260376,
"max": 1.3082289695739746,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11434.0673828125,
"min": 11434.0673828125,
"max": 39686.43359375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989972.0,
"min": 29918.0,
"max": 989972.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989972.0,
"min": 29918.0,
"max": 989972.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.679132878780365,
"min": -0.10702621936798096,
"max": 0.679132878780365,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 200.34420776367188,
"min": -25.793319702148438,
"max": 200.34420776367188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007896408438682556,
"min": -0.08405923843383789,
"max": 0.5228535532951355,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.3294403553009033,
"min": -22.443817138671875,
"max": 123.91629028320312,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06766395730660876,
"min": 0.06499671780398958,
"max": 0.07236415538594507,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9472954022925227,
"min": 0.5789132430875605,
"max": 1.07601493546584,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017007369416585212,
"min": 0.0013760215217509255,
"max": 0.019163748331179488,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23810317183219298,
"min": 0.015136236739260182,
"max": 0.2701058026238267,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.420018955264288e-06,
"min": 7.420018955264288e-06,
"max": 0.000295207576597475,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010388026537370004,
"min": 0.00010388026537370004,
"max": 0.003634581188472999,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247330714285716,
"min": 0.10247330714285716,
"max": 0.198402525,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4346263000000001,
"min": 1.4346263000000001,
"max": 2.6115270000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025708338357142865,
"min": 0.00025708338357142865,
"max": 0.0098404122475,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003599167370000001,
"min": 0.003599167370000001,
"max": 0.12117154730000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012571076862514019,
"min": 0.012571076862514019,
"max": 0.5472290515899658,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1759950816631317,
"min": 0.1759950816631317,
"max": 4.377832412719727,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 275.9909090909091,
"min": 275.9909090909091,
"max": 990.8823529411765,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30359.0,
"min": 16845.0,
"max": 32803.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6694399812004783,
"min": -0.9121937996242195,
"max": 1.6694399812004783,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 183.6383979320526,
"min": -29.190201587975025,
"max": 183.6383979320526,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6694399812004783,
"min": -0.9121937996242195,
"max": 1.6694399812004783,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 183.6383979320526,
"min": -29.190201587975025,
"max": 183.6383979320526,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0359502355378936,
"min": 0.0359502355378936,
"max": 11.698344672427458,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.9545259091682965,
"min": 3.781955229729647,
"max": 198.87185943126678,
"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": "1673834013",
"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=./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": "1.21.6",
"end_time_seconds": "1673836160"
},
"total": 2146.276148422,
"count": 1,
"self": 0.4240876459998617,
"children": {
"run_training.setup": {
"total": 0.12772575899998628,
"count": 1,
"self": 0.12772575899998628
},
"TrainerController.start_learning": {
"total": 2145.724335017,
"count": 1,
"self": 1.1970219290651585,
"children": {
"TrainerController._reset_env": {
"total": 6.337220288000026,
"count": 1,
"self": 6.337220288000026
},
"TrainerController.advance": {
"total": 2138.0905627009347,
"count": 64132,
"self": 1.26951013601456,
"children": {
"env_step": {
"total": 1467.6658171499682,
"count": 64132,
"self": 1363.2647221979737,
"children": {
"SubprocessEnvManager._take_step": {
"total": 103.63138397300372,
"count": 64132,
"self": 4.353232978947062,
"children": {
"TorchPolicy.evaluate": {
"total": 99.27815099405666,
"count": 62545,
"self": 33.69469159807045,
"children": {
"TorchPolicy.sample_actions": {
"total": 65.58345939598621,
"count": 62545,
"self": 65.58345939598621
}
}
}
}
},
"workers": {
"total": 0.7697109789908154,
"count": 64132,
"self": 0.0,
"children": {
"worker_root": {
"total": 2141.119154538951,
"count": 64132,
"is_parallel": true,
"self": 879.6519693499495,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017219629999090103,
"count": 1,
"is_parallel": true,
"self": 0.0006332940004085685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010886689995004417,
"count": 8,
"is_parallel": true,
"self": 0.0010886689995004417
}
}
},
"UnityEnvironment.step": {
"total": 0.04625653300013255,
"count": 1,
"is_parallel": true,
"self": 0.0004936419998102792,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005019100001391053,
"count": 1,
"is_parallel": true,
"self": 0.0005019100001391053
},
"communicator.exchange": {
"total": 0.04340447000004133,
"count": 1,
"is_parallel": true,
"self": 0.04340447000004133
},
"steps_from_proto": {
"total": 0.0018565110001418361,
"count": 1,
"is_parallel": true,
"self": 0.0006071840002732642,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012493269998685719,
"count": 8,
"is_parallel": true,
"self": 0.0012493269998685719
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.4671851890016,
"count": 64131,
"is_parallel": true,
"self": 28.270698283022966,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.357750395006178,
"count": 64131,
"is_parallel": true,
"self": 24.357750395006178
},
"communicator.exchange": {
"total": 1102.7503897829274,
"count": 64131,
"is_parallel": true,
"self": 1102.7503897829274
},
"steps_from_proto": {
"total": 106.08834672804505,
"count": 64131,
"is_parallel": true,
"self": 23.578677538844886,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.50966918920017,
"count": 513048,
"is_parallel": true,
"self": 82.50966918920017
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 669.1552354149521,
"count": 64132,
"self": 2.3291047629672903,
"children": {
"process_trajectory": {
"total": 150.93141726398585,
"count": 64132,
"self": 150.73630484398632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.195112419999532,
"count": 2,
"self": 0.195112419999532
}
}
},
"_update_policy": {
"total": 515.894713387999,
"count": 460,
"self": 203.32672387405773,
"children": {
"TorchPPOOptimizer.update": {
"total": 312.56798951394126,
"count": 22812,
"self": 312.56798951394126
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1249999261053745e-06,
"count": 1,
"self": 1.1249999261053745e-06
},
"TrainerController._save_models": {
"total": 0.09952897400034999,
"count": 1,
"self": 0.0014450860003307753,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09808388800001921,
"count": 1,
"self": 0.09808388800001921
}
}
}
}
}
}
}