diskya's picture
First Push
f6bfabc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7259909510612488,
"min": 0.7189080715179443,
"max": 2.4937682151794434,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 36255.98828125,
"min": 35799.46484375,
"max": 125992.6484375,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 49936.0,
"max": 499976.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.690314292907715,
"min": 2.7988035678863525,
"max": 13.690314292907715,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 13731.384765625,
"min": 2776.4130859375,
"max": 13731.384765625,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 50347.0,
"min": 48158.0,
"max": 50347.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07127030308361552,
"min": 0.06719854030922559,
"max": 0.07127030308361552,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 1.6392169709231572,
"min": 1.4796960634743228,
"max": 1.6392169709231572,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17337385913752537,
"min": 0.1694733767126324,
"max": 0.23536248077008834,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 3.9875987601630833,
"min": 3.8178099406992683,
"max": 5.413337057712032,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.4932895022400003e-05,
"min": 1.4932895022400003e-05,
"max": 0.00028487280504239996,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.0003434565855152001,
"min": 0.0003434565855152001,
"max": 0.006267201710932799,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10497759999999999,
"min": 0.10497759999999999,
"max": 0.19495760000000004,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 2.4144848,
"min": 2.4144848,
"max": 4.289067200000001,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002583822400000001,
"min": 0.0002583822400000001,
"max": 0.0047483842399999995,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0059427915200000025,
"min": 0.0059427915200000025,
"max": 0.10446445328,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.92490118577075,
"min": 9.446280991735538,
"max": 26.92490118577075,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 6812.0,
"min": 2286.0,
"max": 6812.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.92490118577075,
"min": 9.446280991735538,
"max": 26.92490118577075,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 6812.0,
"min": 2286.0,
"max": 6812.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709499621",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "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": "1709500800"
},
"total": 1178.8581679099998,
"count": 1,
"self": 0.7903819569996813,
"children": {
"run_training.setup": {
"total": 0.060534329999882175,
"count": 1,
"self": 0.060534329999882175
},
"TrainerController.start_learning": {
"total": 1178.0072516230002,
"count": 1,
"self": 1.5970998008888273,
"children": {
"TrainerController._reset_env": {
"total": 2.476194513000337,
"count": 1,
"self": 2.476194513000337
},
"TrainerController.advance": {
"total": 1173.796025899111,
"count": 45488,
"self": 0.7817646301577952,
"children": {
"env_step": {
"total": 1173.0142612689533,
"count": 45488,
"self": 765.5920683249165,
"children": {
"SubprocessEnvManager._take_step": {
"total": 406.66029105497046,
"count": 45488,
"self": 3.9392573679829184,
"children": {
"TorchPolicy.evaluate": {
"total": 402.72103368698754,
"count": 45488,
"self": 402.72103368698754
}
}
},
"workers": {
"total": 0.7619018890663938,
"count": 45488,
"self": 0.0,
"children": {
"worker_root": {
"total": 1174.7510162879435,
"count": 45488,
"is_parallel": true,
"self": 577.354583602927,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004899453000234644,
"count": 1,
"is_parallel": true,
"self": 0.0035237170004620566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001375735999772587,
"count": 10,
"is_parallel": true,
"self": 0.001375735999772587
}
}
},
"UnityEnvironment.step": {
"total": 0.043074289000287536,
"count": 1,
"is_parallel": true,
"self": 0.0007800339999448624,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044293200016909395,
"count": 1,
"is_parallel": true,
"self": 0.00044293200016909395
},
"communicator.exchange": {
"total": 0.03959283600033814,
"count": 1,
"is_parallel": true,
"self": 0.03959283600033814
},
"steps_from_proto": {
"total": 0.0022584869998354407,
"count": 1,
"is_parallel": true,
"self": 0.0004820549997930357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001776432000042405,
"count": 10,
"is_parallel": true,
"self": 0.001776432000042405
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 597.3964326850164,
"count": 45487,
"is_parallel": true,
"self": 28.035644626003887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.597404826967704,
"count": 45487,
"is_parallel": true,
"self": 14.597404826967704
},
"communicator.exchange": {
"total": 461.9811172190084,
"count": 45487,
"is_parallel": true,
"self": 461.9811172190084
},
"steps_from_proto": {
"total": 92.7822660130364,
"count": 45487,
"is_parallel": true,
"self": 17.353096685759283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.42916932727712,
"count": 454870,
"is_parallel": true,
"self": 75.42916932727712
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015381799994429457,
"count": 1,
"self": 0.00015381799994429457,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1158.9072580992902,
"count": 1653635,
"is_parallel": true,
"self": 38.88468562542084,
"children": {
"process_trajectory": {
"total": 639.8866490768683,
"count": 1653635,
"is_parallel": true,
"self": 638.3308168348676,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5558322420006334,
"count": 10,
"is_parallel": true,
"self": 1.5558322420006334
}
}
},
"_update_policy": {
"total": 480.1359233970011,
"count": 227,
"is_parallel": true,
"self": 138.50884924701313,
"children": {
"TorchPPOOptimizer.update": {
"total": 341.62707414998795,
"count": 11571,
"is_parallel": true,
"self": 341.62707414998795
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13777759200002038,
"count": 1,
"self": 0.002647497999987536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13513009400003284,
"count": 1,
"self": 0.13513009400003284
}
}
}
}
}
}
}