abhishekkmr13's picture
First Push
fd97843 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9108408689498901,
"min": 0.9108408689498901,
"max": 2.8624207973480225,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8756.82421875,
"min": 8756.82421875,
"max": 29314.05078125,
"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": 12.990630149841309,
"min": 0.40697991847991943,
"max": 12.990630149841309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.1728515625,
"min": 78.9541015625,
"max": 2625.64453125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06855330445264995,
"min": 0.058258198203083,
"max": 0.0727341652580756,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2742132178105998,
"min": 0.233032792812332,
"max": 0.36367082629037806,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19904110923993823,
"min": 0.11957142272206281,
"max": 0.28746970564711327,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7961644369597529,
"min": 0.47828569088825124,
"max": 1.4373485282355662,
"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": 25.568181818181817,
"min": 3.590909090909091,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 158.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.590909090909091,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 158.0,
"max": 1406.0,
"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": "1723776098",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723776578"
},
"total": 479.23004050500015,
"count": 1,
"self": 0.4278957760001276,
"children": {
"run_training.setup": {
"total": 0.06380329500007065,
"count": 1,
"self": 0.06380329500007065
},
"TrainerController.start_learning": {
"total": 478.73834143399995,
"count": 1,
"self": 0.6735031700105765,
"children": {
"TrainerController._reset_env": {
"total": 2.861751226000024,
"count": 1,
"self": 2.861751226000024
},
"TrainerController.advance": {
"total": 475.0857862579893,
"count": 18222,
"self": 0.30236227396483173,
"children": {
"env_step": {
"total": 474.78342398402447,
"count": 18222,
"self": 309.4013122670359,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.06306040100628,
"count": 18222,
"self": 1.5923086190230151,
"children": {
"TorchPolicy.evaluate": {
"total": 163.47075178198327,
"count": 18222,
"self": 163.47075178198327
}
}
},
"workers": {
"total": 0.31905131598227854,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.39096870800506,
"count": 18222,
"is_parallel": true,
"self": 241.35633115500116,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006225785000083306,
"count": 1,
"is_parallel": true,
"self": 0.004688461999990068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001537323000093238,
"count": 10,
"is_parallel": true,
"self": 0.001537323000093238
}
}
},
"UnityEnvironment.step": {
"total": 0.04048345599994718,
"count": 1,
"is_parallel": true,
"self": 0.0007111740000027567,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004314310000381738,
"count": 1,
"is_parallel": true,
"self": 0.0004314310000381738
},
"communicator.exchange": {
"total": 0.03735842999992656,
"count": 1,
"is_parallel": true,
"self": 0.03735842999992656
},
"steps_from_proto": {
"total": 0.001982420999979695,
"count": 1,
"is_parallel": true,
"self": 0.00041244300018661306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015699779997930818,
"count": 10,
"is_parallel": true,
"self": 0.0015699779997930818
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.0346375530039,
"count": 18221,
"is_parallel": true,
"self": 10.489622177016258,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5794171280018645,
"count": 18221,
"is_parallel": true,
"self": 5.5794171280018645
},
"communicator.exchange": {
"total": 184.1731117429988,
"count": 18221,
"is_parallel": true,
"self": 184.1731117429988
},
"steps_from_proto": {
"total": 35.79248650498698,
"count": 18221,
"is_parallel": true,
"self": 7.0529202140075995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.739566290979383,
"count": 182210,
"is_parallel": true,
"self": 28.739566290979383
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015723500018793857,
"count": 1,
"self": 0.00015723500018793857,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 468.95062566501963,
"count": 722594,
"is_parallel": true,
"self": 15.180449846904025,
"children": {
"process_trajectory": {
"total": 262.53299582311627,
"count": 722594,
"is_parallel": true,
"self": 261.29362116911636,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2393746539999029,
"count": 4,
"is_parallel": true,
"self": 1.2393746539999029
}
}
},
"_update_policy": {
"total": 191.23717999499934,
"count": 90,
"is_parallel": true,
"self": 60.78898058400455,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.4481994109948,
"count": 4587,
"is_parallel": true,
"self": 130.4481994109948
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11714354499986257,
"count": 1,
"self": 0.001206142999990334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11593740199987224,
"count": 1,
"self": 0.11593740199987224
}
}
}
}
}
}
}