jaybeeja's picture
Snowball Target
ff757c1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8996767997741699,
"min": 0.8996767997741699,
"max": 2.86702299118042,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8609.9072265625,
"min": 8609.9072265625,
"max": 29329.64453125,
"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": 12.902318954467773,
"min": 0.4879186153411865,
"max": 12.902318954467773,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.9521484375,
"min": 94.65621185302734,
"max": 2612.221435546875,
"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": 0.07069529257711894,
"min": 0.06548431605130876,
"max": 0.07773055065532816,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28278117030847577,
"min": 0.26193726420523505,
"max": 0.38865275327664084,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18754791702125587,
"min": 0.12979003143104195,
"max": 0.29276713013064626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7501916680850235,
"min": 0.5191601257241678,
"max": 1.3508364277727463,
"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": 25.386363636363637,
"min": 3.7954545454545454,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 167.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.7954545454545454,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 167.0,
"max": 1387.0,
"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": "1680066953",
"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": "1680067491"
},
"total": 537.4859620130001,
"count": 1,
"self": 0.43307184300010704,
"children": {
"run_training.setup": {
"total": 0.11803746599997567,
"count": 1,
"self": 0.11803746599997567
},
"TrainerController.start_learning": {
"total": 536.934852704,
"count": 1,
"self": 0.6826106910001499,
"children": {
"TrainerController._reset_env": {
"total": 9.28535576600001,
"count": 1,
"self": 9.28535576600001
},
"TrainerController.advance": {
"total": 526.8068176769998,
"count": 18204,
"self": 0.34002770600613985,
"children": {
"env_step": {
"total": 526.4667899709937,
"count": 18204,
"self": 385.05901794699037,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.07982456500395,
"count": 18204,
"self": 3.026892466008519,
"children": {
"TorchPolicy.evaluate": {
"total": 138.05293209899543,
"count": 18204,
"self": 138.05293209899543
}
}
},
"workers": {
"total": 0.32794745899934696,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 534.7644065639989,
"count": 18204,
"is_parallel": true,
"self": 252.2100629199894,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005154445000016494,
"count": 1,
"is_parallel": true,
"self": 0.0034976990001496233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001656745999866871,
"count": 10,
"is_parallel": true,
"self": 0.001656745999866871
}
}
},
"UnityEnvironment.step": {
"total": 0.099101007999991,
"count": 1,
"is_parallel": true,
"self": 0.0006177339999453579,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000622163000002729,
"count": 1,
"is_parallel": true,
"self": 0.000622163000002729
},
"communicator.exchange": {
"total": 0.0960183900000402,
"count": 1,
"is_parallel": true,
"self": 0.0960183900000402
},
"steps_from_proto": {
"total": 0.0018427210000027117,
"count": 1,
"is_parallel": true,
"self": 0.00037975599997253084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014629650000301808,
"count": 10,
"is_parallel": true,
"self": 0.0014629650000301808
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 282.5543436440095,
"count": 18203,
"is_parallel": true,
"self": 11.057988000008265,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.792546787994922,
"count": 18203,
"is_parallel": true,
"self": 5.792546787994922
},
"communicator.exchange": {
"total": 229.4786366670072,
"count": 18203,
"is_parallel": true,
"self": 229.4786366670072
},
"steps_from_proto": {
"total": 36.225172188999125,
"count": 18203,
"is_parallel": true,
"self": 7.39619525201158,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.828976936987544,
"count": 182030,
"is_parallel": true,
"self": 28.828976936987544
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017754099997091544,
"count": 1,
"self": 0.00017754099997091544,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 522.5795740589364,
"count": 486669,
"is_parallel": true,
"self": 12.346576871910315,
"children": {
"process_trajectory": {
"total": 290.2386051290254,
"count": 486669,
"is_parallel": true,
"self": 289.2740258120255,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9645793169999024,
"count": 4,
"is_parallel": true,
"self": 0.9645793169999024
}
}
},
"_update_policy": {
"total": 219.99439205800064,
"count": 90,
"is_parallel": true,
"self": 87.07916198800024,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.9152300700004,
"count": 4587,
"is_parallel": true,
"self": 132.9152300700004
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15989102900005037,
"count": 1,
"self": 0.000991471000020283,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15889955800003008,
"count": 1,
"self": 0.15889955800003008
}
}
}
}
}
}
}