ppo-Pyramids / run_logs /timers.json
kingkw1's picture
First Push
62de0d4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4460143744945526,
"min": 0.4422111213207245,
"max": 1.4422082901000977,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13351.88671875,
"min": 13281.439453125,
"max": 43750.83203125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989908.0,
"min": 29952.0,
"max": 989908.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989908.0,
"min": 29952.0,
"max": 989908.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.613349437713623,
"min": -0.09968533366918564,
"max": 0.6463828086853027,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 169.89779663085938,
"min": -23.924480438232422,
"max": 183.57272338867188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014922304078936577,
"min": -0.05419567972421646,
"max": 0.3327523469924927,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.133478164672852,
"min": -14.199268341064453,
"max": 78.8623046875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06882139880187986,
"min": 0.0645520282171977,
"max": 0.07376767180389633,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9634995832263181,
"min": 0.48399313260940297,
"max": 1.0804917740249804,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01618189637970534,
"min": 0.00013379621468010005,
"max": 0.022125655036818768,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22654654931587478,
"min": 0.0018731470055214007,
"max": 0.30975917051546276,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.52834034772857e-06,
"min": 7.52834034772857e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010539676486819998,
"min": 0.00010539676486819998,
"max": 0.0035086580304474,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250941428571429,
"min": 0.10250941428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351318000000002,
"min": 1.3886848,
"max": 2.5695526,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002606904871428571,
"min": 0.0002606904871428571,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036496668199999995,
"min": 0.0036496668199999995,
"max": 0.11697830474,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007811293005943298,
"min": 0.007811293005943298,
"max": 0.48905059695243835,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10935810208320618,
"min": 0.10935810208320618,
"max": 3.423354148864746,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 305.5,
"min": 305.5,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28717.0,
"min": 15984.0,
"max": 32360.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6524552994586053,
"min": -1.0000000521540642,
"max": 1.6899262947471518,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 155.3307981491089,
"min": -30.38700169324875,
"max": 160.54299800097942,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6524552994586053,
"min": -1.0000000521540642,
"max": 1.6899262947471518,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 155.3307981491089,
"min": -30.38700169324875,
"max": 160.54299800097942,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.024606567114886353,
"min": 0.024606567114886353,
"max": 10.84311904758215,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.313017308799317,
"min": 2.313017308799317,
"max": 173.4899047613144,
"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": "1675374813",
"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": "1.21.6",
"end_time_seconds": "1675376842"
},
"total": 2029.1151171580002,
"count": 1,
"self": 0.44328088699990076,
"children": {
"run_training.setup": {
"total": 0.11382567200007543,
"count": 1,
"self": 0.11382567200007543
},
"TrainerController.start_learning": {
"total": 2028.5580105990002,
"count": 1,
"self": 1.360351752015049,
"children": {
"TrainerController._reset_env": {
"total": 6.166517204999991,
"count": 1,
"self": 6.166517204999991
},
"TrainerController.advance": {
"total": 2020.943772363985,
"count": 63793,
"self": 1.4318271060180905,
"children": {
"env_step": {
"total": 1361.6948689969606,
"count": 63793,
"self": 1249.3441218059486,
"children": {
"SubprocessEnvManager._take_step": {
"total": 111.4816987880256,
"count": 63793,
"self": 4.429260530069769,
"children": {
"TorchPolicy.evaluate": {
"total": 107.05243825795583,
"count": 62552,
"self": 35.57000179289753,
"children": {
"TorchPolicy.sample_actions": {
"total": 71.4824364650583,
"count": 62552,
"self": 71.4824364650583
}
}
}
}
},
"workers": {
"total": 0.8690484029864365,
"count": 63793,
"self": 0.0,
"children": {
"worker_root": {
"total": 2024.0565175630009,
"count": 63793,
"is_parallel": true,
"self": 876.205107740979,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016584330001023773,
"count": 1,
"is_parallel": true,
"self": 0.0006129329999566835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010455000001456938,
"count": 8,
"is_parallel": true,
"self": 0.0010455000001456938
}
}
},
"UnityEnvironment.step": {
"total": 0.04829925700005333,
"count": 1,
"is_parallel": true,
"self": 0.000466246000087267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004887800000688003,
"count": 1,
"is_parallel": true,
"self": 0.0004887800000688003
},
"communicator.exchange": {
"total": 0.0458297229999971,
"count": 1,
"is_parallel": true,
"self": 0.0458297229999971
},
"steps_from_proto": {
"total": 0.001514507999900161,
"count": 1,
"is_parallel": true,
"self": 0.000371646000075998,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001142861999824163,
"count": 8,
"is_parallel": true,
"self": 0.001142861999824163
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1147.8514098220219,
"count": 63792,
"is_parallel": true,
"self": 28.459872972052835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.915838504977273,
"count": 63792,
"is_parallel": true,
"self": 21.915838504977273
},
"communicator.exchange": {
"total": 999.0612416509732,
"count": 63792,
"is_parallel": true,
"self": 999.0612416509732
},
"steps_from_proto": {
"total": 98.41445669401855,
"count": 63792,
"is_parallel": true,
"self": 22.184696459079078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.22976023493948,
"count": 510336,
"is_parallel": true,
"self": 76.22976023493948
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 657.8170762610064,
"count": 63793,
"self": 2.713385589097925,
"children": {
"process_trajectory": {
"total": 142.29725661090743,
"count": 63793,
"self": 142.1150477459073,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18220886500012057,
"count": 2,
"self": 0.18220886500012057
}
}
},
"_update_policy": {
"total": 512.806434061001,
"count": 452,
"self": 192.7950894029816,
"children": {
"TorchPPOOptimizer.update": {
"total": 320.0113446580194,
"count": 22821,
"self": 320.0113446580194
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2740001693600789e-06,
"count": 1,
"self": 1.2740001693600789e-06
},
"TrainerController._save_models": {
"total": 0.08736800399992717,
"count": 1,
"self": 0.0013803339998048614,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08598767000012231,
"count": 1,
"self": 0.08598767000012231
}
}
}
}
}
}
}