labicquette's picture
First Push
40b9905
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0695147514343262,
"min": 1.0695147514343262,
"max": 2.861666679382324,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10235.255859375,
"min": 10235.255859375,
"max": 29400.763671875,
"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": 12.904687881469727,
"min": 0.3095664978027344,
"max": 12.904687881469727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2516.4140625,
"min": 60.05590057373047,
"max": 2583.19189453125,
"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": 0.06816481765460647,
"min": 0.06132929696732568,
"max": 0.07477055780319086,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2726592706184259,
"min": 0.24531718786930273,
"max": 0.3738527890159543,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18731189007852592,
"min": 0.1460538850161338,
"max": 0.2933848778443301,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7492475603141037,
"min": 0.5842155400645352,
"max": 1.4669243892216506,
"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": 25.84090909090909,
"min": 4.0227272727272725,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 177.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 4.0227272727272725,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 177.0,
"max": 1399.0,
"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": "1683969759",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683970217"
},
"total": 458.413759366,
"count": 1,
"self": 0.43260622000002513,
"children": {
"run_training.setup": {
"total": 0.04104620700013584,
"count": 1,
"self": 0.04104620700013584
},
"TrainerController.start_learning": {
"total": 457.94010693899986,
"count": 1,
"self": 0.5450331940085107,
"children": {
"TrainerController._reset_env": {
"total": 3.7834173329999885,
"count": 1,
"self": 3.7834173329999885
},
"TrainerController.advance": {
"total": 453.4759816719909,
"count": 18204,
"self": 0.28149674598898855,
"children": {
"env_step": {
"total": 453.1944849260019,
"count": 18204,
"self": 333.4799466500085,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.43707255200138,
"count": 18204,
"self": 1.764468405009893,
"children": {
"TorchPolicy.evaluate": {
"total": 117.67260414699149,
"count": 18204,
"self": 117.67260414699149
}
}
},
"workers": {
"total": 0.27746572399200886,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.2871989990092,
"count": 18204,
"is_parallel": true,
"self": 213.33794552401764,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005485488999966037,
"count": 1,
"is_parallel": true,
"self": 0.0041111780003575404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013743109996084968,
"count": 10,
"is_parallel": true,
"self": 0.0013743109996084968
}
}
},
"UnityEnvironment.step": {
"total": 0.03906595500006915,
"count": 1,
"is_parallel": true,
"self": 0.0004160020002927922,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034884699994108814,
"count": 1,
"is_parallel": true,
"self": 0.00034884699994108814
},
"communicator.exchange": {
"total": 0.03631357099993693,
"count": 1,
"is_parallel": true,
"self": 0.03631357099993693
},
"steps_from_proto": {
"total": 0.001987534999898344,
"count": 1,
"is_parallel": true,
"self": 0.0003673509997952351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016201840001031087,
"count": 10,
"is_parallel": true,
"self": 0.0016201840001031087
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.94925347499156,
"count": 18203,
"is_parallel": true,
"self": 9.656234551995112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.380643533989087,
"count": 18203,
"is_parallel": true,
"self": 5.380643533989087
},
"communicator.exchange": {
"total": 195.8350015470205,
"count": 18203,
"is_parallel": true,
"self": 195.8350015470205
},
"steps_from_proto": {
"total": 32.077373841986855,
"count": 18203,
"is_parallel": true,
"self": 6.21908089205499,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.858292949931865,
"count": 182030,
"is_parallel": true,
"self": 25.858292949931865
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010378000024502398,
"count": 1,
"self": 0.00010378000024502398,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.30257318199233,
"count": 414589,
"is_parallel": true,
"self": 8.978354768046756,
"children": {
"process_trajectory": {
"total": 245.52054502994497,
"count": 414589,
"is_parallel": true,
"self": 243.87667019994478,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6438748300001862,
"count": 4,
"is_parallel": true,
"self": 1.6438748300001862
}
}
},
"_update_policy": {
"total": 195.8036733840006,
"count": 90,
"is_parallel": true,
"self": 75.77572971400627,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.02794366999433,
"count": 4584,
"is_parallel": true,
"self": 120.02794366999433
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13557096000022284,
"count": 1,
"self": 0.0009142210005848028,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13465673899963804,
"count": 1,
"self": 0.13465673899963804
}
}
}
}
}
}
}