Gyaneshere's picture
First Push
00b0c42 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8367933630943298,
"min": 0.8367933630943298,
"max": 2.8349242210388184,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7952.88427734375,
"min": 7952.88427734375,
"max": 28938.90625,
"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": 13.01375675201416,
"min": 0.3130321204662323,
"max": 13.01375675201416,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2537.6826171875,
"min": 60.72822952270508,
"max": 2642.744140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07083001310192961,
"min": 0.061188901367987616,
"max": 0.07263609303946736,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28332005240771846,
"min": 0.24475560547195047,
"max": 0.36318046519733677,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18668962233498984,
"min": 0.1266932303791263,
"max": 0.27193109422337775,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7467584893399594,
"min": 0.5067729215165052,
"max": 1.3596554711168887,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.136363636363637,
"min": 3.6136363636363638,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1150.0,
"min": 159.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.136363636363637,
"min": 3.6136363636363638,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1150.0,
"min": 159.0,
"max": 1407.0,
"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": "1738820874",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738821351"
},
"total": 476.69692117600005,
"count": 1,
"self": 0.4901181769999994,
"children": {
"run_training.setup": {
"total": 0.02393249100009598,
"count": 1,
"self": 0.02393249100009598
},
"TrainerController.start_learning": {
"total": 476.18287050799995,
"count": 1,
"self": 0.43166672500876757,
"children": {
"TrainerController._reset_env": {
"total": 3.275994495999953,
"count": 1,
"self": 3.275994495999953
},
"TrainerController.advance": {
"total": 472.3795932409912,
"count": 18192,
"self": 0.4379901259643475,
"children": {
"env_step": {
"total": 334.41635506100863,
"count": 18192,
"self": 254.74130587502304,
"children": {
"SubprocessEnvManager._take_step": {
"total": 79.42960155798596,
"count": 18192,
"self": 1.4333318909959871,
"children": {
"TorchPolicy.evaluate": {
"total": 77.99626966698997,
"count": 18192,
"self": 77.99626966698997
}
}
},
"workers": {
"total": 0.24544762799962427,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.5025836709917,
"count": 18192,
"is_parallel": true,
"self": 251.80298155399305,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006359664999990855,
"count": 1,
"is_parallel": true,
"self": 0.004778441999974348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015812230000165073,
"count": 10,
"is_parallel": true,
"self": 0.0015812230000165073
}
}
},
"UnityEnvironment.step": {
"total": 0.03876238399993781,
"count": 1,
"is_parallel": true,
"self": 0.0006432759998915571,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004659270000502147,
"count": 1,
"is_parallel": true,
"self": 0.0004659270000502147
},
"communicator.exchange": {
"total": 0.03573089400003937,
"count": 1,
"is_parallel": true,
"self": 0.03573089400003937
},
"steps_from_proto": {
"total": 0.0019222869999566683,
"count": 1,
"is_parallel": true,
"self": 0.0003871799998478309,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015351070001088374,
"count": 10,
"is_parallel": true,
"self": 0.0015351070001088374
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.69960211699868,
"count": 18191,
"is_parallel": true,
"self": 10.628736655019793,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.670304226990083,
"count": 18191,
"is_parallel": true,
"self": 5.670304226990083
},
"communicator.exchange": {
"total": 172.81529595500274,
"count": 18191,
"is_parallel": true,
"self": 172.81529595500274
},
"steps_from_proto": {
"total": 33.58526527998606,
"count": 18191,
"is_parallel": true,
"self": 6.058120857987319,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.52714442199874,
"count": 181910,
"is_parallel": true,
"self": 27.52714442199874
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 137.52524805401822,
"count": 18192,
"self": 0.5301292150177233,
"children": {
"process_trajectory": {
"total": 29.410637725000697,
"count": 18192,
"self": 28.80990278800084,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6007349369998565,
"count": 4,
"self": 0.6007349369998565
}
}
},
"_update_policy": {
"total": 107.5844811139998,
"count": 90,
"self": 43.57763564000015,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.00684547399965,
"count": 4587,
"self": 64.00684547399965
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.41999963085982e-07,
"count": 1,
"self": 8.41999963085982e-07
},
"TrainerController._save_models": {
"total": 0.09561520400006884,
"count": 1,
"self": 0.0009808519998841803,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09463435200018466,
"count": 1,
"self": 0.09463435200018466
}
}
}
}
}
}
}