akanametov's picture
Trained SnowballTarget agent upload
857dd12
raw
history blame
19 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6842654943466187,
"min": 0.6585708856582642,
"max": 2.8669607639312744,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7045.197265625,
"min": 6266.3017578125,
"max": 29329.0078125,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.316854476928711,
"min": 0.5071741938591003,
"max": 14.503100395202637,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2934.955078125,
"min": 98.39179229736328,
"max": 2966.3935546875,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06498781699877273,
"min": 0.059435700111470056,
"max": 0.07974589565419592,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.32493908499386365,
"min": 0.24175110601537003,
"max": 0.3987294782709796,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16084062839839972,
"min": 0.13000560533620564,
"max": 0.2675454196392321,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8042031419919986,
"min": 0.5200224213448226,
"max": 1.3377270981961606,
"count": 200
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032997656000039e-07,
"min": 7.032997656000039e-07,
"max": 0.00029918820027059994,
"count": 200
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5164988280000196e-06,
"min": 3.5164988280000196e-06,
"max": 0.0014885160038279998,
"count": 200
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10023440000000002,
"min": 0.10023440000000002,
"max": 0.1997294,
"count": 200
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5011720000000001,
"min": 0.4029176,
"max": 0.996172,
"count": 200
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.1696560000000067e-05,
"min": 2.1696560000000067e-05,
"max": 0.004986497059999999,
"count": 200
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010848280000000034,
"min": 0.00010848280000000034,
"max": 0.024808982800000004,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.818181818181817,
"min": 3.909090909090909,
"max": 28.40909090909091,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1530.0,
"min": 172.0,
"max": 1560.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.818181818181817,
"min": 3.909090909090909,
"max": 28.40909090909091,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1530.0,
"min": 172.0,
"max": 1560.0,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673457178",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673461222"
},
"total": 4044.071929865,
"count": 1,
"self": 0.3886715559997356,
"children": {
"run_training.setup": {
"total": 0.1093614679999746,
"count": 1,
"self": 0.1093614679999746
},
"TrainerController.start_learning": {
"total": 4043.5738968410005,
"count": 1,
"self": 4.748366612919654,
"children": {
"TrainerController._reset_env": {
"total": 7.472251443999994,
"count": 1,
"self": 7.472251443999994
},
"TrainerController.advance": {
"total": 4031.23671099208,
"count": 181873,
"self": 2.376114061205044,
"children": {
"env_step": {
"total": 4028.860596930875,
"count": 181873,
"self": 2613.810338152799,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1412.5374822040235,
"count": 181873,
"self": 13.594108594963018,
"children": {
"TorchPolicy.evaluate": {
"total": 1398.9433736090605,
"count": 181873,
"self": 313.5508216142739,
"children": {
"TorchPolicy.sample_actions": {
"total": 1085.3925519947866,
"count": 181873,
"self": 1085.3925519947866
}
}
}
}
},
"workers": {
"total": 2.512776574052509,
"count": 181873,
"self": 0.0,
"children": {
"worker_root": {
"total": 4032.2127861501162,
"count": 181873,
"is_parallel": true,
"self": 1932.6208630251517,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006449565000025359,
"count": 1,
"is_parallel": true,
"self": 0.003821614000230511,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002627950999794848,
"count": 10,
"is_parallel": true,
"self": 0.002627950999794848
}
}
},
"UnityEnvironment.step": {
"total": 0.031784923000031995,
"count": 1,
"is_parallel": true,
"self": 0.0003347200000689554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022066299993639404,
"count": 1,
"is_parallel": true,
"self": 0.00022066299993639404
},
"communicator.exchange": {
"total": 0.029510478000020157,
"count": 1,
"is_parallel": true,
"self": 0.029510478000020157
},
"steps_from_proto": {
"total": 0.0017190620000064882,
"count": 1,
"is_parallel": true,
"self": 0.0004088260000116861,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013102359999948021,
"count": 10,
"is_parallel": true,
"self": 0.0013102359999948021
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2099.5919231249645,
"count": 181872,
"is_parallel": true,
"self": 81.62233324518593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 47.67572262986869,
"count": 181872,
"is_parallel": true,
"self": 47.67572262986869
},
"communicator.exchange": {
"total": 1678.1447378770172,
"count": 181872,
"is_parallel": true,
"self": 1678.1447378770172
},
"steps_from_proto": {
"total": 292.14912937289273,
"count": 181872,
"is_parallel": true,
"self": 61.20169289411672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 230.947436478776,
"count": 1818720,
"is_parallel": true,
"self": 230.947436478776
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.4927000746829435e-05,
"count": 1,
"self": 5.4927000746829435e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 4004.529954632943,
"count": 3197374,
"is_parallel": true,
"self": 81.67191644184959,
"children": {
"process_trajectory": {
"total": 2277.4287665630904,
"count": 3197374,
"is_parallel": true,
"self": 2270.31834149909,
"children": {
"RLTrainer._checkpoint": {
"total": 7.11042506400031,
"count": 40,
"is_parallel": true,
"self": 7.11042506400031
}
}
},
"_update_policy": {
"total": 1645.4292716280029,
"count": 909,
"is_parallel": true,
"self": 442.0205589010227,
"children": {
"TorchPPOOptimizer.update": {
"total": 1203.4087127269802,
"count": 46353,
"is_parallel": true,
"self": 1203.4087127269802
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11651286500000424,
"count": 1,
"self": 0.0008272420000139391,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1156856229999903,
"count": 1,
"self": 0.1156856229999903
}
}
}
}
}
}
}