jaober's picture
First Push
fe292d0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9675166010856628,
"min": 0.9675166010856628,
"max": 2.8671348094940186,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9248.4912109375,
"min": 9248.4912109375,
"max": 29520.01953125,
"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": 12.907886505126953,
"min": 0.4384479224681854,
"max": 12.907886505126953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2517.037841796875,
"min": 85.05889892578125,
"max": 2625.16357421875,
"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": 0.07437776467750332,
"min": 0.06312332968602777,
"max": 0.07888260048839227,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29751105871001327,
"min": 0.2524933187441111,
"max": 0.36167861363740966,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19653750809968684,
"min": 0.13497940319768317,
"max": 0.29744068226393533,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7861500323987474,
"min": 0.5399176127907327,
"max": 1.2960340808163964,
"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": 26.113636363636363,
"min": 3.590909090909091,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1149.0,
"min": 158.0,
"max": 1403.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.113636363636363,
"min": 3.590909090909091,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1149.0,
"min": 158.0,
"max": 1403.0,
"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": "1693743810",
"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": "1693744289"
},
"total": 478.67136902699997,
"count": 1,
"self": 0.43478499399998327,
"children": {
"run_training.setup": {
"total": 0.04255202499996358,
"count": 1,
"self": 0.04255202499996358
},
"TrainerController.start_learning": {
"total": 478.194032008,
"count": 1,
"self": 0.5877072280023867,
"children": {
"TrainerController._reset_env": {
"total": 4.112515394999946,
"count": 1,
"self": 4.112515394999946
},
"TrainerController.advance": {
"total": 473.35289102899776,
"count": 18201,
"self": 0.31656231298552484,
"children": {
"env_step": {
"total": 473.03632871601224,
"count": 18201,
"self": 346.002163047013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.71954932899303,
"count": 18201,
"self": 1.8565570299953151,
"children": {
"TorchPolicy.evaluate": {
"total": 124.86299229899771,
"count": 18201,
"self": 124.86299229899771
}
}
},
"workers": {
"total": 0.3146163400061823,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.40714880499775,
"count": 18201,
"is_parallel": true,
"self": 220.36148679299265,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005702671999983977,
"count": 1,
"is_parallel": true,
"self": 0.0041828409998743155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015198310001096615,
"count": 10,
"is_parallel": true,
"self": 0.0015198310001096615
}
}
},
"UnityEnvironment.step": {
"total": 0.03519382399997539,
"count": 1,
"is_parallel": true,
"self": 0.0006142389999013176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034461500001725653,
"count": 1,
"is_parallel": true,
"self": 0.00034461500001725653
},
"communicator.exchange": {
"total": 0.031964758000071924,
"count": 1,
"is_parallel": true,
"self": 0.031964758000071924
},
"steps_from_proto": {
"total": 0.0022702119999848946,
"count": 1,
"is_parallel": true,
"self": 0.00043811199986976135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018321000001151333,
"count": 10,
"is_parallel": true,
"self": 0.0018321000001151333
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 256.0456620120051,
"count": 18200,
"is_parallel": true,
"self": 10.788816390015768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.366323924999051,
"count": 18200,
"is_parallel": true,
"self": 5.366323924999051
},
"communicator.exchange": {
"total": 202.91616361399315,
"count": 18200,
"is_parallel": true,
"self": 202.91616361399315
},
"steps_from_proto": {
"total": 36.97435808299713,
"count": 18200,
"is_parallel": true,
"self": 6.931082910012947,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.04327517298418,
"count": 182000,
"is_parallel": true,
"self": 30.04327517298418
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015574899998682668,
"count": 1,
"self": 0.00015574899998682668,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.80775166502644,
"count": 439950,
"is_parallel": true,
"self": 9.668604018046608,
"children": {
"process_trajectory": {
"total": 257.69206069098027,
"count": 439950,
"is_parallel": true,
"self": 256.6715292219802,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0205314690000478,
"count": 4,
"is_parallel": true,
"self": 1.0205314690000478
}
}
},
"_update_policy": {
"total": 202.44708695599957,
"count": 90,
"is_parallel": true,
"self": 79.73061781700301,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.71646913899656,
"count": 4584,
"is_parallel": true,
"self": 122.71646913899656
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14076260699994236,
"count": 1,
"self": 0.0008719359999531662,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1398906709999892,
"count": 1,
"self": 0.1398906709999892
}
}
}
}
}
}
}