chaowu's picture
First Push
abd66b8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.023607611656189,
"min": 1.023607611656189,
"max": 2.867233991622925,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9750.8857421875,
"min": 9750.8857421875,
"max": 29394.8828125,
"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": 12.01995849609375,
"min": 0.29557397961616516,
"max": 12.01995849609375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2343.891845703125,
"min": 57.34135055541992,
"max": 2429.398681640625,
"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": 0.06862524847668942,
"min": 0.0643619679890952,
"max": 0.07562738696002519,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2745009939067577,
"min": 0.2618788032125974,
"max": 0.3736125786238642,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21616593310061621,
"min": 0.12935975829582186,
"max": 0.29431893574256524,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8646637324024649,
"min": 0.5174390331832874,
"max": 1.4350466929814396,
"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": 23.454545454545453,
"min": 3.4545454545454546,
"max": 24.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1032.0,
"min": 152.0,
"max": 1330.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.454545454545453,
"min": 3.4545454545454546,
"max": 24.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1032.0,
"min": 152.0,
"max": 1330.0,
"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": "1687907884",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687908344"
},
"total": 459.92515675100003,
"count": 1,
"self": 0.7914527530000441,
"children": {
"run_training.setup": {
"total": 0.06269663099999434,
"count": 1,
"self": 0.06269663099999434
},
"TrainerController.start_learning": {
"total": 459.071007367,
"count": 1,
"self": 0.5465939509981013,
"children": {
"TrainerController._reset_env": {
"total": 4.916581957999995,
"count": 1,
"self": 4.916581957999995
},
"TrainerController.advance": {
"total": 453.38960714500183,
"count": 18211,
"self": 0.26596416700760983,
"children": {
"env_step": {
"total": 453.1236429779942,
"count": 18211,
"self": 330.4685753779975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.3961935250031,
"count": 18211,
"self": 1.7964760139995235,
"children": {
"TorchPolicy.evaluate": {
"total": 120.59971751100358,
"count": 18211,
"self": 120.59971751100358
}
}
},
"workers": {
"total": 0.2588740749935994,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.3293249700074,
"count": 18211,
"is_parallel": true,
"self": 215.27402288300928,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0069953729999951975,
"count": 1,
"is_parallel": true,
"self": 0.0045661119999920174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00242926100000318,
"count": 10,
"is_parallel": true,
"self": 0.00242926100000318
}
}
},
"UnityEnvironment.step": {
"total": 0.04360723499999608,
"count": 1,
"is_parallel": true,
"self": 0.0006057839999868975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041074300000332187,
"count": 1,
"is_parallel": true,
"self": 0.00041074300000332187
},
"communicator.exchange": {
"total": 0.0405386250000106,
"count": 1,
"is_parallel": true,
"self": 0.0405386250000106
},
"steps_from_proto": {
"total": 0.002052082999995264,
"count": 1,
"is_parallel": true,
"self": 0.0003668749999974352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016852079999978287,
"count": 10,
"is_parallel": true,
"self": 0.0016852079999978287
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.05530208699813,
"count": 18210,
"is_parallel": true,
"self": 10.140635891996482,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.06461673800527,
"count": 18210,
"is_parallel": true,
"self": 5.06461673800527
},
"communicator.exchange": {
"total": 193.22549451099292,
"count": 18210,
"is_parallel": true,
"self": 193.22549451099292
},
"steps_from_proto": {
"total": 33.62455494600346,
"count": 18210,
"is_parallel": true,
"self": 6.0490451540029255,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.57550979200053,
"count": 182100,
"is_parallel": true,
"self": 27.57550979200053
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019374700002572354,
"count": 1,
"self": 0.00019374700002572354,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 449.9535923340112,
"count": 435598,
"is_parallel": true,
"self": 9.55607156601809,
"children": {
"process_trajectory": {
"total": 248.24205072799379,
"count": 435598,
"is_parallel": true,
"self": 247.12375264399384,
"children": {
"RLTrainer._checkpoint": {
"total": 1.118298083999946,
"count": 4,
"is_parallel": true,
"self": 1.118298083999946
}
}
},
"_update_policy": {
"total": 192.15547003999936,
"count": 90,
"is_parallel": true,
"self": 72.48765466000026,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.6678153799991,
"count": 4587,
"is_parallel": true,
"self": 119.6678153799991
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21803056600003856,
"count": 1,
"self": 0.0011149500001010892,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21691561599993747,
"count": 1,
"self": 0.21691561599993747
}
}
}
}
}
}
}