AmrMorgado's picture
First Commit
3ba6058
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3418956398963928,
"min": 0.3418956398963928,
"max": 1.3823819160461426,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10229.517578125,
"min": 10214.6162109375,
"max": 41935.9375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989991.0,
"min": 29946.0,
"max": 989991.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989991.0,
"min": 29946.0,
"max": 989991.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5347107648849487,
"min": -0.1141238808631897,
"max": 0.5956533551216125,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 147.58016967773438,
"min": -27.161483764648438,
"max": 169.76119995117188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.015740860253572464,
"min": -0.021692728623747826,
"max": 0.4905046224594116,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.344477653503418,
"min": -5.791958332061768,
"max": 116.74009704589844,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07270629959280736,
"min": 0.06428511904124419,
"max": 0.07556044438396349,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.017888194299303,
"min": 0.5998449767795899,
"max": 1.057846221375489,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013285563919149961,
"min": 0.00012559794062060958,
"max": 0.018487065985664485,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18599789486809945,
"min": 0.0017583711686885342,
"max": 0.25881892379930277,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.349647550150006e-06,
"min": 7.349647550150006e-06,
"max": 0.0002947677392440875,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010289506570210009,
"min": 0.00010289506570210009,
"max": 0.0037576249474584,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244985,
"min": 0.10244985,
"max": 0.1982559125,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342979,
"min": 1.4342979,
"max": 2.6525416000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002547400150000002,
"min": 0.0002547400150000002,
"max": 0.00982576565875,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003566360210000003,
"min": 0.003566360210000003,
"max": 0.12526890584,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01497010700404644,
"min": 0.01497010700404644,
"max": 0.5134469866752625,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20958149433135986,
"min": 0.20958149433135986,
"max": 4.1075758934021,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 353.3414634146341,
"min": 314.85858585858585,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28974.0,
"min": 17384.0,
"max": 33036.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5490682659352697,
"min": -0.9997267176707586,
"max": 1.6247407203471218,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 127.02359780669212,
"min": -29.991801530122757,
"max": 162.46499889343977,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5490682659352697,
"min": -0.9997267176707586,
"max": 1.6247407203471218,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 127.02359780669212,
"min": -29.991801530122757,
"max": 162.46499889343977,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.055219346880997965,
"min": 0.04957517443002871,
"max": 9.72305309275786,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.527986444241833,
"min": 4.527986444241833,
"max": 175.0149556696415,
"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": "1697813196",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/ppo/PyramidsRND.yaml --env=ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697815351"
},
"total": 2154.5740909749998,
"count": 1,
"self": 0.5385774809997201,
"children": {
"run_training.setup": {
"total": 0.04311320700003307,
"count": 1,
"self": 0.04311320700003307
},
"TrainerController.start_learning": {
"total": 2153.9924002870002,
"count": 1,
"self": 1.3718296679849118,
"children": {
"TrainerController._reset_env": {
"total": 4.110959603999845,
"count": 1,
"self": 4.110959603999845
},
"TrainerController.advance": {
"total": 2148.422808953016,
"count": 63822,
"self": 1.4601956480419176,
"children": {
"env_step": {
"total": 1522.4266696499376,
"count": 63822,
"self": 1388.9504378879783,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.63477569992597,
"count": 63822,
"self": 4.517856013926803,
"children": {
"TorchPolicy.evaluate": {
"total": 128.11691968599916,
"count": 62561,
"self": 128.11691968599916
}
}
},
"workers": {
"total": 0.8414560620333305,
"count": 63822,
"self": 0.0,
"children": {
"worker_root": {
"total": 2149.2436128039994,
"count": 63822,
"is_parallel": true,
"self": 877.890196706958,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018436020000081044,
"count": 1,
"is_parallel": true,
"self": 0.0006395559998964018,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012040460001117026,
"count": 8,
"is_parallel": true,
"self": 0.0012040460001117026
}
}
},
"UnityEnvironment.step": {
"total": 0.08232244400005584,
"count": 1,
"is_parallel": true,
"self": 0.0006462839999130665,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004790870000306313,
"count": 1,
"is_parallel": true,
"self": 0.0004790870000306313
},
"communicator.exchange": {
"total": 0.07914841299998443,
"count": 1,
"is_parallel": true,
"self": 0.07914841299998443
},
"steps_from_proto": {
"total": 0.002048660000127711,
"count": 1,
"is_parallel": true,
"self": 0.00045761699993818183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015910430001895293,
"count": 8,
"is_parallel": true,
"self": 0.0015910430001895293
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1271.3534160970414,
"count": 63821,
"is_parallel": true,
"self": 34.11829676910679,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.029874529992412,
"count": 63821,
"is_parallel": true,
"self": 25.029874529992412
},
"communicator.exchange": {
"total": 1111.831508463975,
"count": 63821,
"is_parallel": true,
"self": 1111.831508463975
},
"steps_from_proto": {
"total": 100.37373633396714,
"count": 63821,
"is_parallel": true,
"self": 20.33835798495329,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.03537834901385,
"count": 510568,
"is_parallel": true,
"self": 80.03537834901385
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 624.5359436550368,
"count": 63822,
"self": 2.5908531860484345,
"children": {
"process_trajectory": {
"total": 123.00297021898405,
"count": 63822,
"self": 122.8383402559839,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1646299630001522,
"count": 2,
"self": 0.1646299630001522
}
}
},
"_update_policy": {
"total": 498.94212025000434,
"count": 460,
"self": 295.50498920999644,
"children": {
"TorchPPOOptimizer.update": {
"total": 203.4371310400079,
"count": 22737,
"self": 203.4371310400079
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3089997992210556e-06,
"count": 1,
"self": 1.3089997992210556e-06
},
"TrainerController._save_models": {
"total": 0.08680075299980672,
"count": 1,
"self": 0.0013183579999349604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08548239499987176,
"count": 1,
"self": 0.08548239499987176
}
}
}
}
}
}
}