pepijn223's picture
First Push
07a9fc5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7020861506462097,
"min": 0.6678435802459717,
"max": 2.8831870555877686,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6757.5791015625,
"min": 6444.51953125,
"max": 29558.43359375,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.336587905883789,
"min": 0.18719394505023956,
"max": 13.336587905883789,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2734.00048828125,
"min": 36.31562423706055,
"max": 2734.00048828125,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.836363636363636,
"min": 2.7954545454545454,
"max": 26.836363636363636,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1476.0,
"min": 123.0,
"max": 1476.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.836363636363636,
"min": 2.7954545454545454,
"max": 26.836363636363636,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1476.0,
"min": 123.0,
"max": 1476.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.047200521688757685,
"min": 0.04239615694214259,
"max": 0.054719337602899244,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09440104337751537,
"min": 0.08479231388428518,
"max": 0.15949399426451646,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18662139013701795,
"min": 0.10040532296760848,
"max": 0.2904681044758535,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3732427802740359,
"min": 0.20081064593521697,
"max": 0.7973586485775954,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.3168988415999968e-06,
"min": 2.3168988415999968e-06,
"max": 0.00019739520130240002,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.6337976831999935e-06,
"min": 4.6337976831999935e-06,
"max": 0.0005578656210672001,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10115840000000001,
"min": 0.10115840000000001,
"max": 0.1986976,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20231680000000002,
"min": 0.20231680000000002,
"max": 0.5789328,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.780415999999992e-05,
"min": 6.780415999999992e-05,
"max": 0.00493501024,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013560831999999984,
"min": 0.00013560831999999984,
"max": 0.013948746719999999,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711044301",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711045420"
},
"total": 1118.750854547,
"count": 1,
"self": 0.43801781099978143,
"children": {
"run_training.setup": {
"total": 0.04916694400003507,
"count": 1,
"self": 0.04916694400003507
},
"TrainerController.start_learning": {
"total": 1118.2636697920002,
"count": 1,
"self": 1.4661858929728169,
"children": {
"TrainerController._reset_env": {
"total": 1.8830164830000058,
"count": 1,
"self": 1.8830164830000058
},
"TrainerController.advance": {
"total": 1114.8195225490272,
"count": 45470,
"self": 0.7584348530565421,
"children": {
"env_step": {
"total": 1114.0610876959706,
"count": 45470,
"self": 733.2629173839914,
"children": {
"SubprocessEnvManager._take_step": {
"total": 380.04217328998106,
"count": 45470,
"self": 3.730284889943391,
"children": {
"TorchPolicy.evaluate": {
"total": 376.3118884000377,
"count": 45470,
"self": 376.3118884000377
}
}
},
"workers": {
"total": 0.7559970219981551,
"count": 45470,
"self": 0.0,
"children": {
"worker_root": {
"total": 1115.3382256719876,
"count": 45470,
"is_parallel": true,
"self": 545.0718076479881,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002339527000003727,
"count": 1,
"is_parallel": true,
"self": 0.0006865989997777433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016529280002259839,
"count": 10,
"is_parallel": true,
"self": 0.0016529280002259839
}
}
},
"UnityEnvironment.step": {
"total": 0.03961121199995432,
"count": 1,
"is_parallel": true,
"self": 0.0007222459998956765,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004383579999966969,
"count": 1,
"is_parallel": true,
"self": 0.0004383579999966969
},
"communicator.exchange": {
"total": 0.036403407000079824,
"count": 1,
"is_parallel": true,
"self": 0.036403407000079824
},
"steps_from_proto": {
"total": 0.002047200999982124,
"count": 1,
"is_parallel": true,
"self": 0.00037907400007952674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016681269999025972,
"count": 10,
"is_parallel": true,
"self": 0.0016681269999025972
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 570.2664180239996,
"count": 45469,
"is_parallel": true,
"self": 26.367805365059326,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.053239061987483,
"count": 45469,
"is_parallel": true,
"self": 14.053239061987483
},
"communicator.exchange": {
"total": 441.8863037679773,
"count": 45469,
"is_parallel": true,
"self": 441.8863037679773
},
"steps_from_proto": {
"total": 87.95906982897543,
"count": 45469,
"is_parallel": true,
"self": 16.670341911956257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.28872791701917,
"count": 454690,
"is_parallel": true,
"self": 71.28872791701917
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013695000006919145,
"count": 1,
"self": 0.00013695000006919145,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1095.3698110068633,
"count": 2269254,
"is_parallel": true,
"self": 49.2096337677533,
"children": {
"process_trajectory": {
"total": 758.5563139661089,
"count": 2269254,
"is_parallel": true,
"self": 757.0495027791085,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5068111870003804,
"count": 10,
"is_parallel": true,
"self": 1.5068111870003804
}
}
},
"_update_policy": {
"total": 287.603863273001,
"count": 113,
"is_parallel": true,
"self": 120.49240809699677,
"children": {
"TorchPPOOptimizer.update": {
"total": 167.11145517600426,
"count": 5748,
"is_parallel": true,
"self": 167.11145517600426
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09480791700002555,
"count": 1,
"self": 0.000970894000147382,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09383702299987817,
"count": 1,
"self": 0.09383702299987817
}
}
}
}
}
}
}