jdawnduan's picture
First Push
d179cf2
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.23150742053985596,
"min": 0.22846980392932892,
"max": 0.2691362202167511,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 6922.998046875,
"min": 2555.206298828125,
"max": 8074.08642578125,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 253.02564102564102,
"min": 242.7,
"max": 300.5353535353535,
"count": 10
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29604.0,
"min": 7281.0,
"max": 31011.0,
"count": 10
},
"Pyramids.Step.mean": {
"value": 1829900.0,
"min": 1559909.0,
"max": 1829900.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 1829900.0,
"min": 1559909.0,
"max": 1829900.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7269483208656311,
"min": 0.636817991733551,
"max": 0.7606475353240967,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 211.54196166992188,
"min": 57.313621520996094,
"max": 224.1884002685547,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0032722465693950653,
"min": -0.0032722465693950653,
"max": 0.049660637974739075,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.9522237777709961,
"min": -0.9522237777709961,
"max": 14.153282165527344,
"count": 10
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7113396412339703,
"min": 1.5989159805327653,
"max": 1.761068951466988,
"count": 10
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 198.51539838314056,
"min": 51.07099959254265,
"max": 210.3139986768365,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7113396412339703,
"min": 1.5989159805327653,
"max": 1.761068951466988,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 198.51539838314056,
"min": 51.07099959254265,
"max": 210.3139986768365,
"count": 10
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.021751641770292894,
"min": 0.020409673645064748,
"max": 0.02597004460491007,
"count": 10
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5231904453539755,
"min": 0.5918805357068777,
"max": 2.7121181183028966,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07101760141925524,
"min": 0.06539173933754985,
"max": 0.07101760141925524,
"count": 10
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9942464198695733,
"min": 0.2731814741855487,
"max": 1.0116279638314154,
"count": 10
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015004975710886579,
"min": 0.012501574646497223,
"max": 0.016779822080732427,
"count": 10
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2100696599524121,
"min": 0.050006298585988894,
"max": 0.2516973312109864,
"count": 10
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.772399234200776e-06,
"min": 5.772399234200776e-06,
"max": 4.780232730916217e-05,
"count": 10
},
"Pyramids.Policy.LearningRate.sum": {
"value": 8.081358927881086e-05,
"min": 8.081358927881086e-05,
"max": 0.0006684922501426485,
"count": 10
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1019241003861004,
"min": 0.1019241003861004,
"max": 0.11593408108108108,
"count": 10
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4269374054054056,
"min": 0.4637363243243243,
"max": 1.7228303243243244,
"count": 10
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00020221762857142874,
"min": 0.00020221762857142874,
"max": 0.0016018147000000003,
"count": 10
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0028310468000000023,
"min": 0.0028310468000000023,
"max": 0.0224107494,
"count": 10
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00821236427873373,
"min": 0.008083767257630825,
"max": 0.008626031689345837,
"count": 10
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11497309803962708,
"min": 0.03239572048187256,
"max": 0.12512154877185822,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688069344",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume --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": "1688070115"
},
"total": 770.9328770510001,
"count": 1,
"self": 0.4763788079999358,
"children": {
"run_training.setup": {
"total": 0.05637150599977758,
"count": 1,
"self": 0.05637150599977758
},
"TrainerController.start_learning": {
"total": 770.4001267370004,
"count": 1,
"self": 0.4115236699644811,
"children": {
"TrainerController._reset_env": {
"total": 4.944524350000393,
"count": 1,
"self": 4.944524350000393
},
"TrainerController.advance": {
"total": 764.9314956250346,
"count": 19720,
"self": 0.4281615950203559,
"children": {
"env_step": {
"total": 574.5986460820031,
"count": 19720,
"self": 541.7861376400015,
"children": {
"SubprocessEnvManager._take_step": {
"total": 32.57480495902382,
"count": 19720,
"self": 1.427109563970589,
"children": {
"TorchPolicy.evaluate": {
"total": 31.147695395053233,
"count": 18805,
"self": 31.147695395053233
}
}
},
"workers": {
"total": 0.2377034829778495,
"count": 19720,
"self": 0.0,
"children": {
"worker_root": {
"total": 768.612088042968,
"count": 19720,
"is_parallel": true,
"self": 261.31560133696894,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028138659999967786,
"count": 1,
"is_parallel": true,
"self": 0.0008333640016644495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001980501998332329,
"count": 8,
"is_parallel": true,
"self": 0.001980501998332329
}
}
},
"UnityEnvironment.step": {
"total": 0.048022279999713646,
"count": 1,
"is_parallel": true,
"self": 0.0005440409995571827,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005040100004407577,
"count": 1,
"is_parallel": true,
"self": 0.0005040100004407577
},
"communicator.exchange": {
"total": 0.04517036499964888,
"count": 1,
"is_parallel": true,
"self": 0.04517036499964888
},
"steps_from_proto": {
"total": 0.0018038640000668238,
"count": 1,
"is_parallel": true,
"self": 0.0003751439980987925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014287200019680313,
"count": 8,
"is_parallel": true,
"self": 0.0014287200019680313
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 507.2964867059991,
"count": 19719,
"is_parallel": true,
"self": 10.142863214824501,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.71222513610428,
"count": 19719,
"is_parallel": true,
"self": 6.71222513610428
},
"communicator.exchange": {
"total": 460.12403952704153,
"count": 19719,
"is_parallel": true,
"self": 460.12403952704153
},
"steps_from_proto": {
"total": 30.317358828028773,
"count": 19719,
"is_parallel": true,
"self": 5.986492605004059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.330866223024714,
"count": 157752,
"is_parallel": true,
"self": 24.330866223024714
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 189.9046879480111,
"count": 19720,
"self": 0.812708965040656,
"children": {
"process_trajectory": {
"total": 33.462418984979195,
"count": 19720,
"self": 33.462418984979195
},
"_update_policy": {
"total": 155.62955999799124,
"count": 142,
"self": 99.70989210594598,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.919667892045254,
"count": 6828,
"self": 55.919667892045254
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3600001693703234e-06,
"count": 1,
"self": 1.3600001693703234e-06
},
"TrainerController._save_models": {
"total": 0.11258173200076271,
"count": 1,
"self": 0.0015809490005267435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11100078300023597,
"count": 1,
"self": 0.11100078300023597
}
}
}
}
}
}
}