Varaprabha's picture
Done
0674aef
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.656657338142395,
"min": 0.6349469423294067,
"max": 2.8719100952148438,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6363.666015625,
"min": 6027.55126953125,
"max": 29474.412109375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.474275588989258,
"min": 0.3318910002708435,
"max": 13.645584106445312,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2762.2265625,
"min": 64.38685607910156,
"max": 2789.3837890625,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06940225943815712,
"min": 0.05890817857854177,
"max": 0.07523924068585021,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3470112971907856,
"min": 0.2471212988893967,
"max": 0.37619620342925103,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16554030513062198,
"min": 0.1155407050174807,
"max": 0.30589529134187043,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.82770152565311,
"min": 0.4621628200699228,
"max": 1.361985750934657,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.418181818181818,
"min": 3.1818181818181817,
"max": 26.727272727272727,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1453.0,
"min": 140.0,
"max": 1464.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.418181818181818,
"min": 3.1818181818181817,
"max": 26.727272727272727,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1453.0,
"min": 140.0,
"max": 1464.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1686201681",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "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": "1686202883"
},
"total": 1202.314200289,
"count": 1,
"self": 0.4298274919999585,
"children": {
"run_training.setup": {
"total": 0.04461901500002341,
"count": 1,
"self": 0.04461901500002341
},
"TrainerController.start_learning": {
"total": 1201.839753782,
"count": 1,
"self": 1.378958014011232,
"children": {
"TrainerController._reset_env": {
"total": 3.8363877000000457,
"count": 1,
"self": 3.8363877000000457
},
"TrainerController.advance": {
"total": 1196.4868504499889,
"count": 45479,
"self": 0.6562818329746278,
"children": {
"env_step": {
"total": 1195.8305686170143,
"count": 45479,
"self": 871.2385368289908,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.9208774150051,
"count": 45479,
"self": 4.780146036024064,
"children": {
"TorchPolicy.evaluate": {
"total": 319.14073137898106,
"count": 45479,
"self": 319.14073137898106
}
}
},
"workers": {
"total": 0.6711543730183394,
"count": 45479,
"self": 0.0,
"children": {
"worker_root": {
"total": 1197.8444510449847,
"count": 45479,
"is_parallel": true,
"self": 556.2875037249648,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005776139000033709,
"count": 1,
"is_parallel": true,
"self": 0.004108965000000353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016671740000333557,
"count": 10,
"is_parallel": true,
"self": 0.0016671740000333557
}
}
},
"UnityEnvironment.step": {
"total": 0.04024111600000424,
"count": 1,
"is_parallel": true,
"self": 0.0007119520000173907,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004554209999696468,
"count": 1,
"is_parallel": true,
"self": 0.0004554209999696468
},
"communicator.exchange": {
"total": 0.036771031000000676,
"count": 1,
"is_parallel": true,
"self": 0.036771031000000676
},
"steps_from_proto": {
"total": 0.002302712000016527,
"count": 1,
"is_parallel": true,
"self": 0.00039987799999607887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001902834000020448,
"count": 10,
"is_parallel": true,
"self": 0.001902834000020448
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 641.5569473200198,
"count": 45478,
"is_parallel": true,
"self": 26.660939556015364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.397334925989583,
"count": 45478,
"is_parallel": true,
"self": 14.397334925989583
},
"communicator.exchange": {
"total": 507.2260148819848,
"count": 45478,
"is_parallel": true,
"self": 507.2260148819848
},
"steps_from_proto": {
"total": 93.27265795603006,
"count": 45478,
"is_parallel": true,
"self": 16.974005866056984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.29865208997307,
"count": 454780,
"is_parallel": true,
"self": 76.29865208997307
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.59050000042771e-05,
"count": 1,
"self": 3.59050000042771e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1186.9652309589321,
"count": 1147062,
"is_parallel": true,
"self": 25.956363981085133,
"children": {
"process_trajectory": {
"total": 649.511135971849,
"count": 1147062,
"is_parallel": true,
"self": 645.9088270698489,
"children": {
"RLTrainer._checkpoint": {
"total": 3.602308902000061,
"count": 10,
"is_parallel": true,
"self": 3.602308902000061
}
}
},
"_update_policy": {
"total": 511.497731005998,
"count": 227,
"is_parallel": true,
"self": 198.9382882079928,
"children": {
"TorchPPOOptimizer.update": {
"total": 312.5594427980052,
"count": 11571,
"is_parallel": true,
"self": 312.5594427980052
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13752171299984184,
"count": 1,
"self": 0.0008349519998773758,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13668676099996446,
"count": 1,
"self": 0.13668676099996446
}
}
}
}
}
}
}