Terps's picture
First Push
b94b2bf
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9894982576370239,
"min": 0.9754210710525513,
"max": 2.8669533729553223,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9480.3828125,
"min": 9480.3828125,
"max": 29549.6875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.786215782165527,
"min": 0.4517129361629486,
"max": 12.806447982788086,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.31201171875,
"min": 87.63230895996094,
"max": 2617.53857421875,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.mean": {
"value": 0.17987486720085144,
"min": 0.10761666297912598,
"max": 0.26051655411720276,
"count": 20
},
"SnowballTarget.Policy.CuriosityValueEstimate.sum": {
"value": 35.075599670410156,
"min": 20.87763214111328,
"max": 53.40589141845703,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06864661709208604,
"min": 0.06325657534191623,
"max": 0.07433176024967586,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27458646836834416,
"min": 0.2530263013676649,
"max": 0.3716588012483793,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.10565935024151614,
"min": 0.05770217951537822,
"max": 0.16127740534972038,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.42263740096606456,
"min": 0.23080871806151287,
"max": 0.8063870267486019,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.mean": {
"value": 0.03605778130027009,
"min": 0.035578419041692046,
"max": 0.1175546848680824,
"count": 20
},
"SnowballTarget.Losses.CuriosityForwardLoss.sum": {
"value": 0.14423112520108036,
"min": 0.14423112520108036,
"max": 0.4702187394723296,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.mean": {
"value": 0.8827689254985136,
"min": 0.8652849678899728,
"max": 2.7858384264012175,
"count": 20
},
"SnowballTarget.Losses.CuriosityInverseLoss.sum": {
"value": 3.5310757019940544,
"min": 3.4890115354575366,
"max": 13.03318906765358,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.022727272727273,
"min": 3.2954545454545454,
"max": 25.022727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1101.0,
"min": 145.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.022727272727273,
"min": 3.2954545454545454,
"max": 25.022727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1101.0,
"min": 145.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.mean": {
"value": 0.37121628858784045,
"min": 0.36311526602049443,
"max": 0.6572515787048774,
"count": 20
},
"SnowballTarget.Policy.CuriosityReward.sum": {
"value": 16.33351669786498,
"min": 16.193131546955556,
"max": 36.14883682876825,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1694619470",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"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": "1694620008"
},
"total": 537.871770708,
"count": 1,
"self": 0.42486783499998637,
"children": {
"run_training.setup": {
"total": 0.07099536200007606,
"count": 1,
"self": 0.07099536200007606
},
"TrainerController.start_learning": {
"total": 537.3759075109999,
"count": 1,
"self": 0.5942737139978362,
"children": {
"TrainerController._reset_env": {
"total": 4.729345418999856,
"count": 1,
"self": 4.729345418999856
},
"TrainerController.advance": {
"total": 531.9056004700019,
"count": 18207,
"self": 0.28875258900757217,
"children": {
"env_step": {
"total": 531.6168478809943,
"count": 18207,
"self": 410.4874470380071,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.82789380598388,
"count": 18207,
"self": 1.8920219630301744,
"children": {
"TorchPolicy.evaluate": {
"total": 118.9358718429537,
"count": 18207,
"self": 118.9358718429537
}
}
},
"workers": {
"total": 0.30150703700337544,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 535.6665731939938,
"count": 18207,
"is_parallel": true,
"self": 284.15536370497443,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003331277999905069,
"count": 1,
"is_parallel": true,
"self": 0.0008317099998293997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024995680000756693,
"count": 10,
"is_parallel": true,
"self": 0.0024995680000756693
}
}
},
"UnityEnvironment.step": {
"total": 0.04511771600004977,
"count": 1,
"is_parallel": true,
"self": 0.0007030890001260559,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042302299993934867,
"count": 1,
"is_parallel": true,
"self": 0.00042302299993934867
},
"communicator.exchange": {
"total": 0.04046062499992331,
"count": 1,
"is_parallel": true,
"self": 0.04046062499992331
},
"steps_from_proto": {
"total": 0.003530979000061052,
"count": 1,
"is_parallel": true,
"self": 0.0015479049998248229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001983074000236229,
"count": 10,
"is_parallel": true,
"self": 0.001983074000236229
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.5112094890194,
"count": 18206,
"is_parallel": true,
"self": 10.637280265021445,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.376301449994344,
"count": 18206,
"is_parallel": true,
"self": 5.376301449994344
},
"communicator.exchange": {
"total": 198.88422318497965,
"count": 18206,
"is_parallel": true,
"self": 198.88422318497965
},
"steps_from_proto": {
"total": 36.61340458902396,
"count": 18206,
"is_parallel": true,
"self": 6.762891233860273,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.850513355163685,
"count": 182060,
"is_parallel": true,
"self": 29.850513355163685
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011929000038435333,
"count": 1,
"self": 0.00011929000038435333,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 528.7277012818795,
"count": 395869,
"is_parallel": true,
"self": 8.865601085034768,
"children": {
"process_trajectory": {
"total": 270.5945444238446,
"count": 395869,
"is_parallel": true,
"self": 269.1041468868448,
"children": {
"RLTrainer._checkpoint": {
"total": 1.490397536999808,
"count": 4,
"is_parallel": true,
"self": 1.490397536999808
}
}
},
"_update_policy": {
"total": 249.26755577300014,
"count": 90,
"is_parallel": true,
"self": 155.99453570301625,
"children": {
"TorchPPOOptimizer.update": {
"total": 93.27302006998389,
"count": 4584,
"is_parallel": true,
"self": 93.27302006998389
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14656861799994658,
"count": 1,
"self": 0.0010552509997978632,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14551336700014872,
"count": 1,
"self": 0.14551336700014872
}
}
}
}
}
}
}