nondevs's picture
First Push
4478c67
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9311292767524719,
"min": 0.9311292767524719,
"max": 2.8679556846618652,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8900.6650390625,
"min": 8900.6650390625,
"max": 29528.47265625,
"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": 12.258877754211426,
"min": 0.44645050168037415,
"max": 12.258877754211426,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2390.481201171875,
"min": 86.61139678955078,
"max": 2472.029052734375,
"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": 0.06966356919554742,
"min": 0.06397436720526814,
"max": 0.07428109470293194,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2786542767821897,
"min": 0.25589746882107256,
"max": 0.3511565012872155,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21006813565013455,
"min": 0.12238777209958975,
"max": 0.2729947247925927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8402725426005382,
"min": 0.489551088398359,
"max": 1.3649736239629635,
"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": 24.34090909090909,
"min": 3.522727272727273,
"max": 24.69090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1071.0,
"min": 155.0,
"max": 1358.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.34090909090909,
"min": 3.522727272727273,
"max": 24.69090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1071.0,
"min": 155.0,
"max": 1358.0,
"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": "1699695052",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699695525"
},
"total": 473.724153209,
"count": 1,
"self": 0.424222364000002,
"children": {
"run_training.setup": {
"total": 0.04991420700002891,
"count": 1,
"self": 0.04991420700002891
},
"TrainerController.start_learning": {
"total": 473.250016638,
"count": 1,
"self": 0.5026472519921867,
"children": {
"TrainerController._reset_env": {
"total": 8.979062045000035,
"count": 1,
"self": 8.979062045000035
},
"TrainerController.advance": {
"total": 463.68493009200773,
"count": 18200,
"self": 0.24715713999341915,
"children": {
"env_step": {
"total": 463.4377729520143,
"count": 18200,
"self": 323.5731381270013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.6040452740042,
"count": 18200,
"self": 1.4164203359978274,
"children": {
"TorchPolicy.evaluate": {
"total": 138.18762493800637,
"count": 18200,
"self": 138.18762493800637
}
}
},
"workers": {
"total": 0.2605895510088203,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.89879343198913,
"count": 18200,
"is_parallel": true,
"self": 232.54148375798593,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005089676000011423,
"count": 1,
"is_parallel": true,
"self": 0.003627246000064588,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014624299999468349,
"count": 10,
"is_parallel": true,
"self": 0.0014624299999468349
}
}
},
"UnityEnvironment.step": {
"total": 0.034730519999982334,
"count": 1,
"is_parallel": true,
"self": 0.00065360899998268,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038355499998488085,
"count": 1,
"is_parallel": true,
"self": 0.00038355499998488085
},
"communicator.exchange": {
"total": 0.0318146299999853,
"count": 1,
"is_parallel": true,
"self": 0.0318146299999853
},
"steps_from_proto": {
"total": 0.0018787260000294737,
"count": 1,
"is_parallel": true,
"self": 0.000373753000076249,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015049729999532246,
"count": 10,
"is_parallel": true,
"self": 0.0015049729999532246
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.3573096740032,
"count": 18199,
"is_parallel": true,
"self": 10.314716640991207,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.273539092003205,
"count": 18199,
"is_parallel": true,
"self": 5.273539092003205
},
"communicator.exchange": {
"total": 191.012185881005,
"count": 18199,
"is_parallel": true,
"self": 191.012185881005
},
"steps_from_proto": {
"total": 32.7568680600038,
"count": 18199,
"is_parallel": true,
"self": 6.0845645429969295,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.672303517006867,
"count": 181990,
"is_parallel": true,
"self": 26.672303517006867
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014631500005179987,
"count": 1,
"self": 0.00014631500005179987,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.78958041098855,
"count": 499237,
"is_parallel": true,
"self": 10.078281139018657,
"children": {
"process_trajectory": {
"total": 259.81084198397025,
"count": 499237,
"is_parallel": true,
"self": 259.30576495697017,
"children": {
"RLTrainer._checkpoint": {
"total": 0.505077027000084,
"count": 4,
"is_parallel": true,
"self": 0.505077027000084
}
}
},
"_update_policy": {
"total": 189.90045728799964,
"count": 90,
"is_parallel": true,
"self": 67.4213317040003,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.47912558399935,
"count": 4587,
"is_parallel": true,
"self": 122.47912558399935
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08323093399997106,
"count": 1,
"self": 0.000832485999922028,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08239844800004903,
"count": 1,
"self": 0.08239844800004903
}
}
}
}
}
}
}