zhanjun520's picture
First Push
6c1b482 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8308377861976624,
"min": 0.8308377861976624,
"max": 2.8680667877197266,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7941.978515625,
"min": 7941.978515625,
"max": 29371.87109375,
"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": 12.660703659057617,
"min": 0.43644532561302185,
"max": 12.660703659057617,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.837158203125,
"min": 84.67039489746094,
"max": 2543.330078125,
"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": 0.06653418184792184,
"min": 0.060288296815997455,
"max": 0.07520552644995869,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26613672739168737,
"min": 0.24115318726398982,
"max": 0.3660336135745085,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21171419541625416,
"min": 0.10632376606672017,
"max": 0.27353786479900866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8468567816650167,
"min": 0.4252950642668807,
"max": 1.3216923659338673,
"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": 25.386363636363637,
"min": 3.477272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 153.0,
"max": 1367.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.477272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 153.0,
"max": 1367.0,
"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": "1707123496",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707123967"
},
"total": 470.9235076240001,
"count": 1,
"self": 0.43987703800007694,
"children": {
"run_training.setup": {
"total": 0.055012323999903856,
"count": 1,
"self": 0.055012323999903856
},
"TrainerController.start_learning": {
"total": 470.4286182620001,
"count": 1,
"self": 0.5958623749924072,
"children": {
"TrainerController._reset_env": {
"total": 3.1868034020000096,
"count": 1,
"self": 3.1868034020000096
},
"TrainerController.advance": {
"total": 466.5507270090077,
"count": 18200,
"self": 0.30954577499892366,
"children": {
"env_step": {
"total": 466.24118123400876,
"count": 18200,
"self": 301.86620300201366,
"children": {
"SubprocessEnvManager._take_step": {
"total": 164.07542039499833,
"count": 18200,
"self": 1.5368199809830685,
"children": {
"TorchPolicy.evaluate": {
"total": 162.53860041401526,
"count": 18200,
"self": 162.53860041401526
}
}
},
"workers": {
"total": 0.29955783699676886,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.1422332320027,
"count": 18200,
"is_parallel": true,
"self": 231.59821966401887,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005407507999962036,
"count": 1,
"is_parallel": true,
"self": 0.003665856999987227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017416509999748087,
"count": 10,
"is_parallel": true,
"self": 0.0017416509999748087
}
}
},
"UnityEnvironment.step": {
"total": 0.041709856000011314,
"count": 1,
"is_parallel": true,
"self": 0.0007682659999090902,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004727120000325158,
"count": 1,
"is_parallel": true,
"self": 0.0004727120000325158
},
"communicator.exchange": {
"total": 0.03801033600007031,
"count": 1,
"is_parallel": true,
"self": 0.03801033600007031
},
"steps_from_proto": {
"total": 0.0024585419999993974,
"count": 1,
"is_parallel": true,
"self": 0.0004553700001679317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020031719998314657,
"count": 10,
"is_parallel": true,
"self": 0.0020031719998314657
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.54401356798382,
"count": 18199,
"is_parallel": true,
"self": 11.285335389933039,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.894951209026317,
"count": 18199,
"is_parallel": true,
"self": 5.894951209026317
},
"communicator.exchange": {
"total": 183.51434604201302,
"count": 18199,
"is_parallel": true,
"self": 183.51434604201302
},
"steps_from_proto": {
"total": 36.84938092701145,
"count": 18199,
"is_parallel": true,
"self": 6.834468855990281,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.014912071021172,
"count": 181990,
"is_parallel": true,
"self": 30.014912071021172
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013652799998453702,
"count": 1,
"self": 0.00013652799998453702,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 460.0680459439242,
"count": 709482,
"is_parallel": true,
"self": 15.79087853292458,
"children": {
"process_trajectory": {
"total": 254.85357853700043,
"count": 709482,
"is_parallel": true,
"self": 253.99277282000025,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8608057170001757,
"count": 4,
"is_parallel": true,
"self": 0.8608057170001757
}
}
},
"_update_policy": {
"total": 189.42358887399917,
"count": 90,
"is_parallel": true,
"self": 52.31445898900256,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.1091298849966,
"count": 4584,
"is_parallel": true,
"self": 137.1091298849966
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09508894800001144,
"count": 1,
"self": 0.001051005000135774,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09403794299987567,
"count": 1,
"self": 0.09403794299987567
}
}
}
}
}
}
}