aaronrmm's picture
First Push
5abba1b
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9032449722290039,
"min": 0.9032449722290039,
"max": 2.857100248336792,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8653.990234375,
"min": 8653.990234375,
"max": 29259.564453125,
"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": 13.027348518371582,
"min": 0.3522356152534485,
"max": 13.027348518371582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.3330078125,
"min": 68.33370971679688,
"max": 2639.150390625,
"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": 0.06981740922059561,
"min": 0.062291158015261104,
"max": 0.07658626642118108,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27926963688238243,
"min": 0.24916463206104442,
"max": 0.37802613170146393,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20163289917742505,
"min": 0.11599729596591535,
"max": 0.2935082942393481,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8065315967097002,
"min": 0.4639891838636614,
"max": 1.4284547812798443,
"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": 25.65909090909091,
"min": 3.590909090909091,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1129.0,
"min": 158.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.65909090909091,
"min": 3.590909090909091,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1129.0,
"min": 158.0,
"max": 1393.0,
"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": "1684553866",
"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": "1684554308"
},
"total": 441.7214426820001,
"count": 1,
"self": 0.3886590540002999,
"children": {
"run_training.setup": {
"total": 0.03935164199992869,
"count": 1,
"self": 0.03935164199992869
},
"TrainerController.start_learning": {
"total": 441.29343198599986,
"count": 1,
"self": 0.5013129049950749,
"children": {
"TrainerController._reset_env": {
"total": 3.7957540370000515,
"count": 1,
"self": 3.7957540370000515
},
"TrainerController.advance": {
"total": 436.86519774000476,
"count": 18205,
"self": 0.2476202180200744,
"children": {
"env_step": {
"total": 436.6175775219847,
"count": 18205,
"self": 315.820907580985,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.55876063500364,
"count": 18205,
"self": 1.6599832980111842,
"children": {
"TorchPolicy.evaluate": {
"total": 118.89877733699245,
"count": 18205,
"self": 118.89877733699245
}
}
},
"workers": {
"total": 0.2379093059960269,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.8950419069886,
"count": 18205,
"is_parallel": true,
"self": 209.00957936998861,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053635500000837055,
"count": 1,
"is_parallel": true,
"self": 0.003932649000716992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014309009993667132,
"count": 10,
"is_parallel": true,
"self": 0.0014309009993667132
}
}
},
"UnityEnvironment.step": {
"total": 0.04780905100005839,
"count": 1,
"is_parallel": true,
"self": 0.0005781720001323265,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003167969998685294,
"count": 1,
"is_parallel": true,
"self": 0.0003167969998685294
},
"communicator.exchange": {
"total": 0.044934418000138976,
"count": 1,
"is_parallel": true,
"self": 0.044934418000138976
},
"steps_from_proto": {
"total": 0.0019796639999185572,
"count": 1,
"is_parallel": true,
"self": 0.00036667799963652215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001612986000282035,
"count": 10,
"is_parallel": true,
"self": 0.001612986000282035
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.88546253699997,
"count": 18204,
"is_parallel": true,
"self": 9.390738166986466,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.051872214016612,
"count": 18204,
"is_parallel": true,
"self": 5.051872214016612
},
"communicator.exchange": {
"total": 184.6498563879925,
"count": 18204,
"is_parallel": true,
"self": 184.6498563879925
},
"steps_from_proto": {
"total": 31.792995768004403,
"count": 18204,
"is_parallel": true,
"self": 5.961672026978704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.8313237410257,
"count": 182040,
"is_parallel": true,
"self": 25.8313237410257
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001153529999555758,
"count": 1,
"self": 0.0001153529999555758,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 433.4772747599077,
"count": 417529,
"is_parallel": true,
"self": 9.299758755995981,
"children": {
"process_trajectory": {
"total": 236.56591981491215,
"count": 417529,
"is_parallel": true,
"self": 234.95075651691218,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6151632979999704,
"count": 4,
"is_parallel": true,
"self": 1.6151632979999704
}
}
},
"_update_policy": {
"total": 187.61159618899956,
"count": 90,
"is_parallel": true,
"self": 70.23090881699909,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.38068737200047,
"count": 4587,
"is_parallel": true,
"self": 117.38068737200047
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13105195100001765,
"count": 1,
"self": 0.000843669999994745,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1302082810000229,
"count": 1,
"self": 0.1302082810000229
}
}
}
}
}
}
}