ninja21's picture
First Push
7cc5586 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9140187501907349,
"min": 0.9140187501907349,
"max": 2.8712000846862793,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8747.1591796875,
"min": 8747.1591796875,
"max": 29467.126953125,
"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": 12.880391120910645,
"min": 0.460464209318161,
"max": 12.880391120910645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.67626953125,
"min": 89.3300552368164,
"max": 2612.702392578125,
"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": 0.06921054200753204,
"min": 0.05959127373224713,
"max": 0.07442810544949571,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2768421680301282,
"min": 0.23836509492898852,
"max": 0.3721405272474786,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1925669701441246,
"min": 0.1301944896352806,
"max": 0.2749956573049227,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7702678805764984,
"min": 0.5207779585411224,
"max": 1.3238314299606808,
"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": 25.59090909090909,
"min": 3.522727272727273,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 155.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.522727272727273,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 155.0,
"max": 1378.0,
"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": "1711111742",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711112445"
},
"total": 702.8323725770001,
"count": 1,
"self": 1.1919814750001478,
"children": {
"run_training.setup": {
"total": 0.08227188099999694,
"count": 1,
"self": 0.08227188099999694
},
"TrainerController.start_learning": {
"total": 701.558119221,
"count": 1,
"self": 1.075068863994602,
"children": {
"TrainerController._reset_env": {
"total": 4.280955005999999,
"count": 1,
"self": 4.280955005999999
},
"TrainerController.advance": {
"total": 696.0035858320056,
"count": 18208,
"self": 0.5030918500208372,
"children": {
"env_step": {
"total": 695.5004939819847,
"count": 18208,
"self": 534.5465527919724,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.4507398370066,
"count": 18208,
"self": 3.295308011007137,
"children": {
"TorchPolicy.evaluate": {
"total": 157.15543182599947,
"count": 18208,
"self": 157.15543182599947
}
}
},
"workers": {
"total": 0.5032013530056929,
"count": 18208,
"self": 0.0,
"children": {
"worker_root": {
"total": 698.8694810370158,
"count": 18208,
"is_parallel": true,
"self": 325.5829418360112,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007953245999942737,
"count": 1,
"is_parallel": true,
"self": 0.0047675649996108405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003185681000331897,
"count": 10,
"is_parallel": true,
"self": 0.003185681000331897
}
}
},
"UnityEnvironment.step": {
"total": 0.05404547699993145,
"count": 1,
"is_parallel": true,
"self": 0.0009564579999050693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005765610000025845,
"count": 1,
"is_parallel": true,
"self": 0.0005765610000025845
},
"communicator.exchange": {
"total": 0.050008359999992535,
"count": 1,
"is_parallel": true,
"self": 0.050008359999992535
},
"steps_from_proto": {
"total": 0.002504098000031263,
"count": 1,
"is_parallel": true,
"self": 0.0004951070000061009,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002008991000025162,
"count": 10,
"is_parallel": true,
"self": 0.002008991000025162
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 373.28653920100464,
"count": 18207,
"is_parallel": true,
"self": 18.415891783027405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.060467283010553,
"count": 18207,
"is_parallel": true,
"self": 9.060467283010553
},
"communicator.exchange": {
"total": 293.6798585119752,
"count": 18207,
"is_parallel": true,
"self": 293.6798585119752
},
"steps_from_proto": {
"total": 52.13032162299146,
"count": 18207,
"is_parallel": true,
"self": 10.718456403003415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.411865219988044,
"count": 182070,
"is_parallel": true,
"self": 41.411865219988044
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021588899994640087,
"count": 1,
"self": 0.00021588899994640087,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 687.4113495809781,
"count": 934473,
"is_parallel": true,
"self": 23.002386865977428,
"children": {
"process_trajectory": {
"total": 374.7380713130009,
"count": 934473,
"is_parallel": true,
"self": 373.6046909980008,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1333803150000676,
"count": 4,
"is_parallel": true,
"self": 1.1333803150000676
}
}
},
"_update_policy": {
"total": 289.6708914019998,
"count": 90,
"is_parallel": true,
"self": 72.8729281289992,
"children": {
"TorchPPOOptimizer.update": {
"total": 216.79796327300062,
"count": 4587,
"is_parallel": true,
"self": 216.79796327300062
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19829362999985278,
"count": 1,
"self": 0.002272296999763057,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19602133300008973,
"count": 1,
"self": 0.19602133300008973
}
}
}
}
}
}
}