ntrant7's picture
First Push
5d6951f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9314693808555603,
"min": 0.9314693808555603,
"max": 2.872642993927002,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8934.654296875,
"min": 8934.654296875,
"max": 29513.53515625,
"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": 12.927793502807617,
"min": 0.4411250650882721,
"max": 12.927793502807617,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.919677734375,
"min": 85.57826232910156,
"max": 2632.6484375,
"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": 0.07439670416936804,
"min": 0.06178229195922416,
"max": 0.07439670416936804,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29758681667747217,
"min": 0.24712916783689665,
"max": 0.35278064090251815,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2029368180562468,
"min": 0.12615193571100997,
"max": 0.27408033850438457,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8117472722249872,
"min": 0.5046077428440399,
"max": 1.3557858572286718,
"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": 25.136363636363637,
"min": 4.0,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 176.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 4.0,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 176.0,
"max": 1409.0,
"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": "1682519620",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/ntrant/anaconda3/envs/rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --force --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+cu113",
"numpy_version": "1.21.2",
"end_time_seconds": "1682519803"
},
"total": 182.78154160897247,
"count": 1,
"self": 0.21760170394554734,
"children": {
"run_training.setup": {
"total": 0.013586868066340685,
"count": 1,
"self": 0.013586868066340685
},
"TrainerController.start_learning": {
"total": 182.5503530369606,
"count": 1,
"self": 0.21137082297354937,
"children": {
"TrainerController._reset_env": {
"total": 2.916545447194949,
"count": 1,
"self": 2.916545447194949
},
"TrainerController.advance": {
"total": 179.35508542973548,
"count": 18207,
"self": 0.11041137436404824,
"children": {
"env_step": {
"total": 179.24467405537143,
"count": 18207,
"self": 129.40163600328378,
"children": {
"SubprocessEnvManager._take_step": {
"total": 49.73253012285568,
"count": 18207,
"self": 0.640473322942853,
"children": {
"TorchPolicy.evaluate": {
"total": 49.092056799912825,
"count": 18207,
"self": 49.092056799912825
}
}
},
"workers": {
"total": 0.1105079292319715,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 182.21936677396297,
"count": 18207,
"is_parallel": true,
"self": 98.1918527551461,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013154230546206236,
"count": 1,
"is_parallel": true,
"self": 0.00036413921043276787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009512838441878557,
"count": 10,
"is_parallel": true,
"self": 0.0009512838441878557
}
}
},
"UnityEnvironment.step": {
"total": 0.016012815991416574,
"count": 1,
"is_parallel": true,
"self": 0.00024982914328575134,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017715897411108017,
"count": 1,
"is_parallel": true,
"self": 0.00017715897411108017
},
"communicator.exchange": {
"total": 0.014776811935007572,
"count": 1,
"is_parallel": true,
"self": 0.014776811935007572
},
"steps_from_proto": {
"total": 0.0008090159390121698,
"count": 1,
"is_parallel": true,
"self": 0.000174299580976367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006347163580358028,
"count": 10,
"is_parallel": true,
"self": 0.0006347163580358028
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 84.02751401881687,
"count": 18206,
"is_parallel": true,
"self": 4.208189357072115,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.1547782712150365,
"count": 18206,
"is_parallel": true,
"self": 2.1547782712150365
},
"communicator.exchange": {
"total": 64.92343107121997,
"count": 18206,
"is_parallel": true,
"self": 64.92343107121997
},
"steps_from_proto": {
"total": 12.741115319309756,
"count": 18206,
"is_parallel": true,
"self": 2.4653044857550412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.275810833554715,
"count": 182060,
"is_parallel": true,
"self": 10.275810833554715
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.901014760136604e-05,
"count": 1,
"self": 7.901014760136604e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 179.24867185857147,
"count": 101976,
"is_parallel": true,
"self": 0.7257212470285594,
"children": {
"process_trajectory": {
"total": 97.12703139823861,
"count": 101976,
"is_parallel": true,
"self": 96.64257265394554,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4844587442930788,
"count": 4,
"is_parallel": true,
"self": 0.4844587442930788
}
}
},
"_update_policy": {
"total": 81.3959192133043,
"count": 90,
"is_parallel": true,
"self": 23.71808963129297,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.67782958201133,
"count": 4587,
"is_parallel": true,
"self": 57.67782958201133
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.06727232690900564,
"count": 1,
"self": 0.00032616802491247654,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06694615888409317,
"count": 1,
"self": 0.06694615888409317
}
}
}
}
}
}
}