khadivi-ah's picture
First Push
b073ef5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.716669499874115,
"min": 0.716669499874115,
"max": 2.865122079849243,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6834.876953125,
"min": 6834.876953125,
"max": 29467.78125,
"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": 12.545422554016113,
"min": 0.33275386691093445,
"max": 12.545422554016113,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2446.357421875,
"min": 64.55425262451172,
"max": 2516.13232421875,
"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": 0.07061167860086368,
"min": 0.059190920932679525,
"max": 0.07738084365479939,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2824467144034547,
"min": 0.24378563238161743,
"max": 0.35719578174586575,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19926018114475644,
"min": 0.10574856165604775,
"max": 0.3419366427058098,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7970407245790257,
"min": 0.422994246624191,
"max": 1.4262151411351036,
"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": 25.181818181818183,
"min": 3.022727272727273,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 133.0,
"max": 1362.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.022727272727273,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 133.0,
"max": 1362.0,
"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": "1724766063",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget --no-graphics",
"mlagents_version": "1.0.0",
"mlagents_envs_version": "1.0.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.21.2",
"end_time_seconds": "1724766484"
},
"total": 420.903944072,
"count": 1,
"self": 0.42424504699999943,
"children": {
"run_training.setup": {
"total": 0.07804396099999167,
"count": 1,
"self": 0.07804396099999167
},
"TrainerController.start_learning": {
"total": 420.401655064,
"count": 1,
"self": 0.5178559039958373,
"children": {
"TrainerController._reset_env": {
"total": 2.2832562110000367,
"count": 1,
"self": 2.2832562110000367
},
"TrainerController.advance": {
"total": 417.51688505600424,
"count": 18201,
"self": 0.24027406400290374,
"children": {
"env_step": {
"total": 417.27661099200134,
"count": 18201,
"self": 267.64086922900424,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.38646723800065,
"count": 18201,
"self": 1.3458761769936132,
"children": {
"TorchPolicy.evaluate": {
"total": 148.04059106100704,
"count": 18201,
"self": 148.04059106100704
}
}
},
"workers": {
"total": 0.24927452499645142,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.36035163799426,
"count": 18201,
"is_parallel": true,
"self": 210.00197754098878,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021108139999910236,
"count": 1,
"is_parallel": true,
"self": 0.0006595399999014262,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014512740000895974,
"count": 10,
"is_parallel": true,
"self": 0.0014512740000895974
}
}
},
"UnityEnvironment.step": {
"total": 0.0349328400000104,
"count": 1,
"is_parallel": true,
"self": 0.000626276999980746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042719100002841515,
"count": 1,
"is_parallel": true,
"self": 0.00042719100002841515
},
"communicator.exchange": {
"total": 0.03176632800000334,
"count": 1,
"is_parallel": true,
"self": 0.03176632800000334
},
"steps_from_proto": {
"total": 0.002113043999997899,
"count": 1,
"is_parallel": true,
"self": 0.0005216460000951884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015913979999027106,
"count": 10,
"is_parallel": true,
"self": 0.0015913979999027106
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.35837409700548,
"count": 18200,
"is_parallel": true,
"self": 9.96610316501284,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.068391439009758,
"count": 18200,
"is_parallel": true,
"self": 5.068391439009758
},
"communicator.exchange": {
"total": 159.2966385259906,
"count": 18200,
"is_parallel": true,
"self": 159.2966385259906
},
"steps_from_proto": {
"total": 35.02724096699228,
"count": 18200,
"is_parallel": true,
"self": 6.153854425015595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.873386541976686,
"count": 182000,
"is_parallel": true,
"self": 28.873386541976686
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001652229999535848,
"count": 1,
"self": 0.0001652229999535848,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 412.4850155769807,
"count": 649189,
"is_parallel": true,
"self": 12.842083877972868,
"children": {
"process_trajectory": {
"total": 222.4477253550079,
"count": 649189,
"is_parallel": true,
"self": 221.65931789700807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7884074579998241,
"count": 4,
"is_parallel": true,
"self": 0.7884074579998241
}
}
},
"_update_policy": {
"total": 177.19520634399993,
"count": 90,
"is_parallel": true,
"self": 59.967551552994564,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.22765479100536,
"count": 4587,
"is_parallel": true,
"self": 117.22765479100536
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08349266999994143,
"count": 1,
"self": 0.0009256719999939378,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08256699799994749,
"count": 1,
"self": 0.08256699799994749
}
}
}
}
}
}
}