Alvin12345's picture
Second Push
fb8d28f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.3649346828460693,
"min": 0.43669629096984863,
"max": 1.709028959274292,
"count": 180
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 14068.3818359375,
"min": 4222.41650390625,
"max": 17024.1875,
"count": 180
},
"SnowballTarget.Step.mean": {
"value": 1999968.0,
"min": 209936.0,
"max": 1999968.0,
"count": 180
},
"SnowballTarget.Step.sum": {
"value": 1999968.0,
"min": 209936.0,
"max": 1999968.0,
"count": 180
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.8407400846481323,
"min": -65.11407470703125,
"max": 12.765594482421875,
"count": 180
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 375.510986328125,
"min": -12697.244140625,
"max": 2450.994140625,
"count": 180
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 180
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 180
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06672238468042116,
"min": 0.05699007155915557,
"max": 0.08241154129533881,
"count": 180
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3336119234021058,
"min": 0.2279602862366223,
"max": 0.4082585538734703,
"count": 180
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 104.026864301588,
"min": 0.11363965425435818,
"max": 2895.1401315552816,
"count": 180
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 520.1343215079401,
"min": 0.46927890998913957,
"max": 11580.560526221127,
"count": 180
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.16499761199997e-07,
"min": 7.16499761199997e-07,
"max": 0.00026917141027619996,
"count": 180
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.582498805999985e-06,
"min": 3.582498805999985e-06,
"max": 0.0013384320538559998,
"count": 180
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1002388,
"min": 0.1002388,
"max": 0.18972380000000003,
"count": 180
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.501194,
"min": 0.40293520000000005,
"max": 0.9461440000000001,
"count": 180
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.191611999999995e-05,
"min": 2.191611999999995e-05,
"max": 0.004487217620000001,
"count": 180
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010958059999999975,
"min": 0.00010958059999999975,
"max": 0.022312585599999997,
"count": 180
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 0.7272727272727273,
"min": 0.6727272727272727,
"max": 23.65909090909091,
"count": 180
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 40.0,
"min": 32.0,
"max": 1043.0,
"count": 180
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 0.7272727272727273,
"min": 0.6727272727272727,
"max": 23.65909090909091,
"count": 180
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 40.0,
"min": 32.0,
"max": 1043.0,
"count": 180
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 180
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 180
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720607817",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/home/sfchan/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --resume --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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720662041"
},
"total": 54224.825508332,
"count": 1,
"self": 0.31917493394576013,
"children": {
"run_training.setup": {
"total": 0.04039233096409589,
"count": 1,
"self": 0.04039233096409589
},
"TrainerController.start_learning": {
"total": 54224.46594106709,
"count": 1,
"self": 2.705630289041437,
"children": {
"TrainerController._reset_env": {
"total": 1.7701998639386147,
"count": 1,
"self": 1.7701998639386147
},
"TrainerController.advance": {
"total": 54219.924458440044,
"count": 163674,
"self": 1.4220840806374326,
"children": {
"env_step": {
"total": 54218.50237435941,
"count": 163674,
"self": 53399.90546932502,
"children": {
"SubprocessEnvManager._take_step": {
"total": 817.0301447720267,
"count": 163674,
"self": 6.8767024266999215,
"children": {
"TorchPolicy.evaluate": {
"total": 810.1534423453268,
"count": 163674,
"self": 810.1534423453268
}
}
},
"workers": {
"total": 1.5667602623580024,
"count": 163674,
"self": 0.0,
"children": {
"worker_root": {
"total": 54220.593177647446,
"count": 163674,
"is_parallel": true,
"self": 52674.53962920967,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00239887204952538,
"count": 1,
"is_parallel": true,
"self": 0.0005935129011049867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018053591484203935,
"count": 10,
"is_parallel": true,
"self": 0.0018053591484203935
}
}
},
"UnityEnvironment.step": {
"total": 0.019515422987751663,
"count": 1,
"is_parallel": true,
"self": 0.0005205328343436122,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032791204284876585,
"count": 1,
"is_parallel": true,
"self": 0.00032791204284876585
},
"communicator.exchange": {
"total": 0.01719974202569574,
"count": 1,
"is_parallel": true,
"self": 0.01719974202569574
},
"steps_from_proto": {
"total": 0.0014672360848635435,
"count": 1,
"is_parallel": true,
"self": 0.0003142228815704584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001153013203293085,
"count": 10,
"is_parallel": true,
"self": 0.001153013203293085
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1546.053548437776,
"count": 163673,
"is_parallel": true,
"self": 72.20992328424472,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 38.59321974567138,
"count": 163673,
"is_parallel": true,
"self": 38.59321974567138
},
"communicator.exchange": {
"total": 1229.6917245928198,
"count": 163673,
"is_parallel": true,
"self": 1229.6917245928198
},
"steps_from_proto": {
"total": 205.55868081504013,
"count": 163673,
"is_parallel": true,
"self": 35.730654022539966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 169.82802679250017,
"count": 1636730,
"is_parallel": true,
"self": 169.82802679250017
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002605150220915675,
"count": 1,
"self": 0.0002605150220915675,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 54203.20641250978,
"count": 4292000,
"is_parallel": true,
"self": 48.35717121628113,
"children": {
"process_trajectory": {
"total": 1480.1030138649512,
"count": 4292000,
"is_parallel": true,
"self": 1475.9344581046607,
"children": {
"RLTrainer._checkpoint": {
"total": 4.168555760290474,
"count": 36,
"is_parallel": true,
"self": 4.168555760290474
}
}
},
"_update_policy": {
"total": 52674.74622742855,
"count": 818,
"is_parallel": true,
"self": 22314.18164149823,
"children": {
"TorchPPOOptimizer.update": {
"total": 30360.56458593032,
"count": 4171500,
"is_parallel": true,
"self": 30360.56458593032
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.06539195904042572,
"count": 1,
"self": 0.0013076640898361802,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06408429495058954,
"count": 1,
"self": 0.06408429495058954
}
}
}
}
}
}
}