dreamboat26's picture
First Push
2407718
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.924700915813446,
"min": 0.924700915813446,
"max": 2.867913246154785,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8869.7314453125,
"min": 8869.7314453125,
"max": 29433.392578125,
"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": 13.040046691894531,
"min": 0.3950407803058624,
"max": 13.040046691894531,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2542.80908203125,
"min": 76.63790893554688,
"max": 2632.63525390625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06431777448989462,
"min": 0.06359196482553135,
"max": 0.07643189184554834,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2572710979595785,
"min": 0.2543678593021254,
"max": 0.35371941597173534,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19289648467127013,
"min": 0.13268337005238032,
"max": 0.30981630327947,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7715859386850805,
"min": 0.5307334802095213,
"max": 1.3684242665767672,
"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": 3.5681818181818183,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1126.0,
"min": 157.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.59090909090909,
"min": 3.5681818181818183,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1126.0,
"min": 157.0,
"max": 1414.0,
"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": "1691183214",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691183813"
},
"total": 599.551387302,
"count": 1,
"self": 0.49073780000003353,
"children": {
"run_training.setup": {
"total": 0.054937017999975524,
"count": 1,
"self": 0.054937017999975524
},
"TrainerController.start_learning": {
"total": 599.005712484,
"count": 1,
"self": 0.8343568779924908,
"children": {
"TrainerController._reset_env": {
"total": 2.8684839670000315,
"count": 1,
"self": 2.8684839670000315
},
"TrainerController.advance": {
"total": 595.1455018490076,
"count": 18206,
"self": 0.4121580390028612,
"children": {
"env_step": {
"total": 594.7333438100047,
"count": 18206,
"self": 486.1572778360041,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.16915927599752,
"count": 18206,
"self": 2.706867459998932,
"children": {
"TorchPolicy.evaluate": {
"total": 105.46229181599858,
"count": 18206,
"self": 105.46229181599858
}
}
},
"workers": {
"total": 0.4069066980031266,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 596.488750185998,
"count": 18206,
"is_parallel": true,
"self": 259.90107187500166,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008542771000008997,
"count": 1,
"is_parallel": true,
"self": 0.005579921999981252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002962849000027745,
"count": 10,
"is_parallel": true,
"self": 0.002962849000027745
}
}
},
"UnityEnvironment.step": {
"total": 0.08472563499998387,
"count": 1,
"is_parallel": true,
"self": 0.0008714130000839759,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004819419999648744,
"count": 1,
"is_parallel": true,
"self": 0.0004819419999648744
},
"communicator.exchange": {
"total": 0.08038529699996388,
"count": 1,
"is_parallel": true,
"self": 0.08038529699996388
},
"steps_from_proto": {
"total": 0.002986982999971133,
"count": 1,
"is_parallel": true,
"self": 0.0007711829999266229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00221580000004451,
"count": 10,
"is_parallel": true,
"self": 0.00221580000004451
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 336.58767831099635,
"count": 18205,
"is_parallel": true,
"self": 14.701027890016405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.05325968099163,
"count": 18205,
"is_parallel": true,
"self": 8.05325968099163
},
"communicator.exchange": {
"total": 264.6091103649912,
"count": 18205,
"is_parallel": true,
"self": 264.6091103649912
},
"steps_from_proto": {
"total": 49.224280374997136,
"count": 18205,
"is_parallel": true,
"self": 9.488928932005251,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.735351442991885,
"count": 182050,
"is_parallel": true,
"self": 39.735351442991885
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013073299999177834,
"count": 1,
"self": 0.00013073299999177834,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 589.745457917976,
"count": 603093,
"is_parallel": true,
"self": 14.344021090918432,
"children": {
"process_trajectory": {
"total": 320.09126390605707,
"count": 603093,
"is_parallel": true,
"self": 318.60559559205717,
"children": {
"RLTrainer._checkpoint": {
"total": 1.485668313999895,
"count": 4,
"is_parallel": true,
"self": 1.485668313999895
}
}
},
"_update_policy": {
"total": 255.31017292100051,
"count": 90,
"is_parallel": true,
"self": 95.97785905800617,
"children": {
"TorchPPOOptimizer.update": {
"total": 159.33231386299434,
"count": 4587,
"is_parallel": true,
"self": 159.33231386299434
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15723905699996976,
"count": 1,
"self": 0.0010964569999032392,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15614260000006652,
"count": 1,
"self": 0.15614260000006652
}
}
}
}
}
}
}