edwardjjj's picture
First Push
8bb902e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9042971730232239,
"min": 0.8815541863441467,
"max": 2.8683199882507324,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8624.2822265625,
"min": 8624.2822265625,
"max": 29437.568359375,
"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": 12.947548866271973,
"min": 0.4181631803512573,
"max": 13.05752182006836,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.77197265625,
"min": 81.1236572265625,
"max": 2663.734375,
"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": 0.07073223306546353,
"min": 0.06336859607744925,
"max": 0.0739387374712547,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2829289322618541,
"min": 0.25784522199754456,
"max": 0.3696936873562735,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20796197287592233,
"min": 0.149284345702743,
"max": 0.28789422523741626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8318478915036893,
"min": 0.597137382810972,
"max": 1.4394711261870814,
"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": 25.022727272727273,
"min": 3.7954545454545454,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1101.0,
"min": 167.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.022727272727273,
"min": 3.7954545454545454,
"max": 25.65909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1101.0,
"min": 167.0,
"max": 1387.0,
"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": "1692250050",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692250560"
},
"total": 509.71901268299996,
"count": 1,
"self": 0.43500062099997194,
"children": {
"run_training.setup": {
"total": 0.06807243599996582,
"count": 1,
"self": 0.06807243599996582
},
"TrainerController.start_learning": {
"total": 509.215939626,
"count": 1,
"self": 0.607795601997168,
"children": {
"TrainerController._reset_env": {
"total": 5.866556857000035,
"count": 1,
"self": 5.866556857000035
},
"TrainerController.advance": {
"total": 502.5895980800029,
"count": 18200,
"self": 0.32536669899923254,
"children": {
"env_step": {
"total": 502.26423138100364,
"count": 18200,
"self": 364.44860313900085,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.50375166300023,
"count": 18200,
"self": 1.8400962180020883,
"children": {
"TorchPolicy.evaluate": {
"total": 135.66365544499814,
"count": 18200,
"self": 135.66365544499814
}
}
},
"workers": {
"total": 0.3118765790025577,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 507.47544968900314,
"count": 18200,
"is_parallel": true,
"self": 239.80504572000768,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.018172468999978264,
"count": 1,
"is_parallel": true,
"self": 0.014178829999877962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003993639000100302,
"count": 10,
"is_parallel": true,
"self": 0.003993639000100302
}
}
},
"UnityEnvironment.step": {
"total": 0.03397860999996283,
"count": 1,
"is_parallel": true,
"self": 0.0007935940000152186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004572720000055597,
"count": 1,
"is_parallel": true,
"self": 0.0004572720000055597
},
"communicator.exchange": {
"total": 0.029680166999980884,
"count": 1,
"is_parallel": true,
"self": 0.029680166999980884
},
"steps_from_proto": {
"total": 0.0030475769999611657,
"count": 1,
"is_parallel": true,
"self": 0.0006860279999045815,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002361549000056584,
"count": 10,
"is_parallel": true,
"self": 0.002361549000056584
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 267.67040396899546,
"count": 18199,
"is_parallel": true,
"self": 11.06289000101566,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.729797299999518,
"count": 18199,
"is_parallel": true,
"self": 5.729797299999518
},
"communicator.exchange": {
"total": 211.17630870999335,
"count": 18199,
"is_parallel": true,
"self": 211.17630870999335
},
"steps_from_proto": {
"total": 39.70140795798693,
"count": 18199,
"is_parallel": true,
"self": 7.272623408012635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.428784549974296,
"count": 181990,
"is_parallel": true,
"self": 32.428784549974296
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001071659999070107,
"count": 1,
"self": 0.0001071659999070107,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 498.5589515229907,
"count": 470637,
"is_parallel": true,
"self": 11.04465276204661,
"children": {
"process_trajectory": {
"total": 274.4362559849435,
"count": 470637,
"is_parallel": true,
"self": 273.66452271194356,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7717332729999384,
"count": 4,
"is_parallel": true,
"self": 0.7717332729999384
}
}
},
"_update_policy": {
"total": 213.0780427760006,
"count": 90,
"is_parallel": true,
"self": 83.44117308100078,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.6368696949998,
"count": 4587,
"is_parallel": true,
"self": 129.6368696949998
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15188192100004017,
"count": 1,
"self": 0.0008780979999301053,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15100382300011006,
"count": 1,
"self": 0.15100382300011006
}
}
}
}
}
}
}