arunptp's picture
Second Push
994d53f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.066102385520935,
"min": 1.066102385520935,
"max": 2.858086109161377,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10167.41796875,
"min": 10167.41796875,
"max": 29301.09765625,
"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": 12.541716575622559,
"min": 0.4094673991203308,
"max": 12.541716575622559,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2445.634765625,
"min": 79.43667602539062,
"max": 2529.3193359375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07432372750960947,
"min": 0.058775277393579024,
"max": 0.07446630856686491,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2972949100384379,
"min": 0.2351011095743161,
"max": 0.36430832491639786,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2197666853374126,
"min": 0.13112692508216509,
"max": 0.2743299653863206,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8790667413496503,
"min": 0.5245077003286603,
"max": 1.2989122680589265,
"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.Environment.CumulativeReward.mean": {
"value": 24.636363636363637,
"min": 3.4545454545454546,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1084.0,
"min": 152.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.636363636363637,
"min": 3.4545454545454546,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1084.0,
"min": 152.0,
"max": 1377.0,
"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": "1698301851",
"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",
"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": "1698302307"
},
"total": 455.8308084499995,
"count": 1,
"self": 0.831404296999608,
"children": {
"run_training.setup": {
"total": 0.04353852799977176,
"count": 1,
"self": 0.04353852799977176
},
"TrainerController.start_learning": {
"total": 454.9558656250001,
"count": 1,
"self": 0.5332198090445672,
"children": {
"TrainerController._reset_env": {
"total": 3.421216371999435,
"count": 1,
"self": 3.421216371999435
},
"TrainerController.advance": {
"total": 450.8920168239565,
"count": 18199,
"self": 0.27668477509450895,
"children": {
"env_step": {
"total": 450.615332048862,
"count": 18199,
"self": 309.9449279106784,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.39424249913918,
"count": 18199,
"self": 1.4174932731148147,
"children": {
"TorchPolicy.evaluate": {
"total": 138.97674922602437,
"count": 18199,
"self": 138.97674922602437
}
}
},
"workers": {
"total": 0.2761616390444033,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.66532801008,
"count": 18199,
"is_parallel": true,
"self": 217.37531352701535,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020397020007294486,
"count": 1,
"is_parallel": true,
"self": 0.0006439410008169943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013957609999124543,
"count": 10,
"is_parallel": true,
"self": 0.0013957609999124543
}
}
},
"UnityEnvironment.step": {
"total": 0.05998032800016517,
"count": 1,
"is_parallel": true,
"self": 0.0006538129991895403,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004087570005140151,
"count": 1,
"is_parallel": true,
"self": 0.0004087570005140151
},
"communicator.exchange": {
"total": 0.05686470300042856,
"count": 1,
"is_parallel": true,
"self": 0.05686470300042856
},
"steps_from_proto": {
"total": 0.002053055000033055,
"count": 1,
"is_parallel": true,
"self": 0.00039246599862963194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001660589001403423,
"count": 10,
"is_parallel": true,
"self": 0.001660589001403423
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.29001448306462,
"count": 18198,
"is_parallel": true,
"self": 10.401308195092497,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.285220339003899,
"count": 18198,
"is_parallel": true,
"self": 5.285220339003899
},
"communicator.exchange": {
"total": 187.65127074996144,
"count": 18198,
"is_parallel": true,
"self": 187.65127074996144
},
"steps_from_proto": {
"total": 32.95221519900679,
"count": 18198,
"is_parallel": true,
"self": 6.138308440998117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.81390675800867,
"count": 181980,
"is_parallel": true,
"self": 26.81390675800867
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015265700039890362,
"count": 1,
"self": 0.00015265700039890362,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.2934113771498,
"count": 457122,
"is_parallel": true,
"self": 9.571740736888387,
"children": {
"process_trajectory": {
"total": 252.45776761225534,
"count": 457122,
"is_parallel": true,
"self": 251.63228572025582,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8254818919995159,
"count": 4,
"is_parallel": true,
"self": 0.8254818919995159
}
}
},
"_update_policy": {
"total": 185.2639030280061,
"count": 90,
"is_parallel": true,
"self": 56.13494278700273,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.12896024100337,
"count": 4587,
"is_parallel": true,
"self": 129.12896024100337
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10925996299920371,
"count": 1,
"self": 0.001578684999003599,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10768127800020011,
"count": 1,
"self": 0.10768127800020011
}
}
}
}
}
}
}