marcweibel's picture
First Push
0f4e828
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.054558277130127,
"min": 1.054558277130127,
"max": 2.872812032699585,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10068.9228515625,
"min": 10068.9228515625,
"max": 29420.46875,
"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": 12.647936820983887,
"min": 0.34243232011795044,
"max": 12.647936820983887,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2466.34765625,
"min": 66.43186950683594,
"max": 2525.67041015625,
"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": 0.0706776059117093,
"min": 0.06308558486699065,
"max": 0.07528553463749169,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2827104236468372,
"min": 0.25977303280995007,
"max": 0.3612362474581904,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18335702989761735,
"min": 0.1200406877232679,
"max": 0.2921770725545346,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7334281195904694,
"min": 0.4801627508930716,
"max": 1.460885362772673,
"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": 0.10134700000000002,
"min": 0.10134700000000002,
"max": 0.148647,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4053880000000001,
"min": 0.4053880000000001,
"max": 0.73086,
"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": 24.818181818181817,
"min": 3.1136363636363638,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1092.0,
"min": 137.0,
"max": 1370.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.818181818181817,
"min": 3.1136363636363638,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1092.0,
"min": 137.0,
"max": 1370.0,
"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": "1702577293",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702577751"
},
"total": 457.34765294900035,
"count": 1,
"self": 0.4887673030007136,
"children": {
"run_training.setup": {
"total": 0.07270210099977703,
"count": 1,
"self": 0.07270210099977703
},
"TrainerController.start_learning": {
"total": 456.78618354499986,
"count": 1,
"self": 0.5848855690051096,
"children": {
"TrainerController._reset_env": {
"total": 4.261338873000113,
"count": 1,
"self": 4.261338873000113
},
"TrainerController.advance": {
"total": 451.85482968099495,
"count": 18200,
"self": 0.27528902200765515,
"children": {
"env_step": {
"total": 451.5795406589873,
"count": 18200,
"self": 297.74358589201256,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.54417262997094,
"count": 18200,
"self": 1.4666198209729373,
"children": {
"TorchPolicy.evaluate": {
"total": 152.077552808998,
"count": 18200,
"self": 152.077552808998
}
}
},
"workers": {
"total": 0.29178213700379274,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.5506357050067,
"count": 18200,
"is_parallel": true,
"self": 225.18727838098448,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006251709000025585,
"count": 1,
"is_parallel": true,
"self": 0.004795463999926142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014562450000994431,
"count": 10,
"is_parallel": true,
"self": 0.0014562450000994431
}
}
},
"UnityEnvironment.step": {
"total": 0.06777387800002543,
"count": 1,
"is_parallel": true,
"self": 0.0006875579997540626,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003781460000027437,
"count": 1,
"is_parallel": true,
"self": 0.0003781460000027437
},
"communicator.exchange": {
"total": 0.06373022500019943,
"count": 1,
"is_parallel": true,
"self": 0.06373022500019943
},
"steps_from_proto": {
"total": 0.002977949000069202,
"count": 1,
"is_parallel": true,
"self": 0.00042090000033567776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025570489997335244,
"count": 10,
"is_parallel": true,
"self": 0.0025570489997335244
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.36335732402222,
"count": 18199,
"is_parallel": true,
"self": 10.682274008073364,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.506331179003155,
"count": 18199,
"is_parallel": true,
"self": 5.506331179003155
},
"communicator.exchange": {
"total": 180.03709436996996,
"count": 18199,
"is_parallel": true,
"self": 180.03709436996996
},
"steps_from_proto": {
"total": 34.137657766975735,
"count": 18199,
"is_parallel": true,
"self": 6.282396540144418,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.855261226831317,
"count": 181990,
"is_parallel": true,
"self": 27.855261226831317
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.309199973955401e-05,
"count": 1,
"self": 3.309199973955401e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.2788128390598,
"count": 667120,
"is_parallel": true,
"self": 13.556426427224778,
"children": {
"process_trajectory": {
"total": 248.7013941638338,
"count": 667120,
"is_parallel": true,
"self": 247.43267578883433,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2687183749994801,
"count": 4,
"is_parallel": true,
"self": 1.2687183749994801
}
}
},
"_update_policy": {
"total": 184.02099224800122,
"count": 90,
"is_parallel": true,
"self": 59.45371553601126,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.56727671198996,
"count": 4584,
"is_parallel": true,
"self": 124.56727671198996
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0850963299999421,
"count": 1,
"self": 0.0009039629999278986,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0841923670000142,
"count": 1,
"self": 0.0841923670000142
}
}
}
}
}
}
}