maidh's picture
First Push
eaab23e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0332400798797607,
"min": 1.0255647897720337,
"max": 2.8536179065704346,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9876.7421875,
"min": 9876.7421875,
"max": 29412.240234375,
"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": 11.99303913116455,
"min": 0.3895837962627411,
"max": 12.122658729553223,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2338.642578125,
"min": 75.57925415039062,
"max": 2469.91552734375,
"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": 0.06963192000351709,
"min": 0.060971665776093024,
"max": 0.07318148749112094,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27852768001406836,
"min": 0.2438866631043721,
"max": 0.36350196117122074,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18829518264415218,
"min": 0.11809926528675373,
"max": 0.31646022142148483,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7531807305766087,
"min": 0.4723970611470149,
"max": 1.4305883429798427,
"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": 23.863636363636363,
"min": 3.5454545454545454,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1050.0,
"min": 156.0,
"max": 1325.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.863636363636363,
"min": 3.5454545454545454,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1050.0,
"min": 156.0,
"max": 1325.0,
"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": "1682253914",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1682254419"
},
"total": 505.55971308900007,
"count": 1,
"self": 0.427033174000087,
"children": {
"run_training.setup": {
"total": 0.20522260900003175,
"count": 1,
"self": 0.20522260900003175
},
"TrainerController.start_learning": {
"total": 504.92745730599995,
"count": 1,
"self": 0.5986474479917661,
"children": {
"TrainerController._reset_env": {
"total": 4.364570921999984,
"count": 1,
"self": 4.364570921999984
},
"TrainerController.advance": {
"total": 499.8178305870082,
"count": 18201,
"self": 0.3470460800136266,
"children": {
"env_step": {
"total": 499.47078450699456,
"count": 18201,
"self": 366.12328015000975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.03329347399313,
"count": 18201,
"self": 1.9843563909956288,
"children": {
"TorchPolicy.evaluate": {
"total": 131.0489370829975,
"count": 18201,
"self": 131.0489370829975
}
}
},
"workers": {
"total": 0.31421088299168787,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 503.3620591419916,
"count": 18201,
"is_parallel": true,
"self": 231.58539510099024,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006072416000051817,
"count": 1,
"is_parallel": true,
"self": 0.003752023000004101,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023203930000477158,
"count": 10,
"is_parallel": true,
"self": 0.0023203930000477158
}
}
},
"UnityEnvironment.step": {
"total": 0.0362363289999621,
"count": 1,
"is_parallel": true,
"self": 0.0006149679999225555,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039740400001164744,
"count": 1,
"is_parallel": true,
"self": 0.00039740400001164744
},
"communicator.exchange": {
"total": 0.03317288499999904,
"count": 1,
"is_parallel": true,
"self": 0.03317288499999904
},
"steps_from_proto": {
"total": 0.002051072000028853,
"count": 1,
"is_parallel": true,
"self": 0.0004034749999846099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001647597000044243,
"count": 10,
"is_parallel": true,
"self": 0.001647597000044243
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 271.77666404100137,
"count": 18200,
"is_parallel": true,
"self": 10.940075641007525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.089302342989981,
"count": 18200,
"is_parallel": true,
"self": 6.089302342989981
},
"communicator.exchange": {
"total": 217.97566519000026,
"count": 18200,
"is_parallel": true,
"self": 217.97566519000026
},
"steps_from_proto": {
"total": 36.771620867003605,
"count": 18200,
"is_parallel": true,
"self": 7.58305117601185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.188569690991756,
"count": 182000,
"is_parallel": true,
"self": 29.188569690991756
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011934600001950457,
"count": 1,
"self": 0.00011934600001950457,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 495.67187216297555,
"count": 442743,
"is_parallel": true,
"self": 11.875462186972811,
"children": {
"process_trajectory": {
"total": 276.025110766003,
"count": 442743,
"is_parallel": true,
"self": 274.81917002800304,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2059407379999811,
"count": 4,
"is_parallel": true,
"self": 1.2059407379999811
}
}
},
"_update_policy": {
"total": 207.7712992099997,
"count": 90,
"is_parallel": true,
"self": 75.96572100099581,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.8055782090039,
"count": 4587,
"is_parallel": true,
"self": 131.8055782090039
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1462890029999926,
"count": 1,
"self": 0.0009749399999918751,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14531406300000071,
"count": 1,
"self": 0.14531406300000071
}
}
}
}
}
}
}