matolszew's picture
Default params
596e311
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9077873826026917,
"min": 0.9077873826026917,
"max": 2.8750948905944824,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8667.5537109375,
"min": 8667.5537109375,
"max": 29443.84765625,
"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": 12.898489952087402,
"min": 0.44215673208236694,
"max": 12.898489952087402,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2515.20556640625,
"min": 85.77840423583984,
"max": 2583.9111328125,
"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": 0.06843896916788984,
"min": 0.06419129328823343,
"max": 0.0732892944615599,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2737558766715594,
"min": 0.25676517315293373,
"max": 0.36644647230779953,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19408224428109094,
"min": 0.09435507567718114,
"max": 0.2887307148353726,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7763289771243638,
"min": 0.37742030270872456,
"max": 1.443653574176863,
"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": 2.9545454545454546,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 130.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 2.9545454545454546,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 130.0,
"max": 1388.0,
"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": "1678216861",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678217340"
},
"total": 478.45833781,
"count": 1,
"self": 0.4415136290000419,
"children": {
"run_training.setup": {
"total": 0.17483058200002688,
"count": 1,
"self": 0.17483058200002688
},
"TrainerController.start_learning": {
"total": 477.8419935989999,
"count": 1,
"self": 0.5726415919888268,
"children": {
"TrainerController._reset_env": {
"total": 8.789291890999948,
"count": 1,
"self": 8.789291890999948
},
"TrainerController.advance": {
"total": 468.3468273950109,
"count": 18202,
"self": 0.2815807890041242,
"children": {
"env_step": {
"total": 468.0652466060068,
"count": 18202,
"self": 322.72844244701173,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.05084983499285,
"count": 18202,
"self": 1.5623564939996868,
"children": {
"TorchPolicy.evaluate": {
"total": 143.48849334099316,
"count": 18202,
"self": 31.315274777974423,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.17321856301874,
"count": 18202,
"self": 112.17321856301874
}
}
}
}
},
"workers": {
"total": 0.2859543240022049,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 476.4623036780039,
"count": 18202,
"is_parallel": true,
"self": 231.02975771100796,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007081946999960564,
"count": 1,
"is_parallel": true,
"self": 0.003993601999695784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030883450002647805,
"count": 10,
"is_parallel": true,
"self": 0.0030883450002647805
}
}
},
"UnityEnvironment.step": {
"total": 0.05411715200000344,
"count": 1,
"is_parallel": true,
"self": 0.0006696309999369987,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005098259999840593,
"count": 1,
"is_parallel": true,
"self": 0.0005098259999840593
},
"communicator.exchange": {
"total": 0.0506955900000321,
"count": 1,
"is_parallel": true,
"self": 0.0506955900000321
},
"steps_from_proto": {
"total": 0.0022421050000502873,
"count": 1,
"is_parallel": true,
"self": 0.00053691600021466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017051889998356273,
"count": 10,
"is_parallel": true,
"self": 0.0017051889998356273
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.43254596699592,
"count": 18201,
"is_parallel": true,
"self": 9.655396558998746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6878015470060745,
"count": 18201,
"is_parallel": true,
"self": 5.6878015470060745
},
"communicator.exchange": {
"total": 196.98996960299746,
"count": 18201,
"is_parallel": true,
"self": 196.98996960299746
},
"steps_from_proto": {
"total": 33.099378257993635,
"count": 18201,
"is_parallel": true,
"self": 7.231469967984708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.867908290008927,
"count": 182010,
"is_parallel": true,
"self": 25.867908290008927
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001883140000700223,
"count": 1,
"self": 0.0001883140000700223,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 464.89136698810853,
"count": 401047,
"is_parallel": true,
"self": 10.528346537123298,
"children": {
"process_trajectory": {
"total": 266.5526811539845,
"count": 401047,
"is_parallel": true,
"self": 265.39666503098476,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1560161229997448,
"count": 4,
"is_parallel": true,
"self": 1.1560161229997448
}
}
},
"_update_policy": {
"total": 187.81033929700072,
"count": 90,
"is_parallel": true,
"self": 67.25409730499359,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.55624199200713,
"count": 4584,
"is_parallel": true,
"self": 120.55624199200713
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1330444070001704,
"count": 1,
"self": 0.000887601000158611,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13215680600001178,
"count": 1,
"self": 0.13215680600001178
}
}
}
}
}
}
}