AlikS's picture
First Push
d90c65c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8332760334014893,
"min": 0.8332760334014893,
"max": 2.8655827045440674,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7965.28564453125,
"min": 7965.28564453125,
"max": 29346.43359375,
"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": 12.847916603088379,
"min": 0.3445104956626892,
"max": 12.847916603088379,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2505.34375,
"min": 66.83503723144531,
"max": 2596.7412109375,
"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": 0.07159744610694094,
"min": 0.06455652833637764,
"max": 0.07667461803651475,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28638978442776375,
"min": 0.26458531205814023,
"max": 0.3829414836780451,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20857653357819014,
"min": 0.13328021125155776,
"max": 0.28616968270610366,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8343061343127606,
"min": 0.533120845006231,
"max": 1.4308484135305182,
"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": 25.795454545454547,
"min": 3.659090909090909,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 161.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 3.659090909090909,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 161.0,
"max": 1381.0,
"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": "1716071466",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716071963"
},
"total": 496.2234068839998,
"count": 1,
"self": 0.43858873499993933,
"children": {
"run_training.setup": {
"total": 0.05604492399970695,
"count": 1,
"self": 0.05604492399970695
},
"TrainerController.start_learning": {
"total": 495.72877322500017,
"count": 1,
"self": 0.6349535960375761,
"children": {
"TrainerController._reset_env": {
"total": 3.511101098999916,
"count": 1,
"self": 3.511101098999916
},
"TrainerController.advance": {
"total": 491.49306716096316,
"count": 18199,
"self": 0.31782745794589573,
"children": {
"env_step": {
"total": 491.17523970301727,
"count": 18199,
"self": 323.03984506504094,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.80812844997536,
"count": 18199,
"self": 1.6927606869867304,
"children": {
"TorchPolicy.evaluate": {
"total": 166.11536776298863,
"count": 18199,
"self": 166.11536776298863
}
}
},
"workers": {
"total": 0.3272661880009764,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 494.2931752249724,
"count": 18199,
"is_parallel": true,
"self": 249.02768624896908,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006583941000371851,
"count": 1,
"is_parallel": true,
"self": 0.004345119999470626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022388210009012255,
"count": 10,
"is_parallel": true,
"self": 0.0022388210009012255
}
}
},
"UnityEnvironment.step": {
"total": 0.04266074499992101,
"count": 1,
"is_parallel": true,
"self": 0.0008038619998842478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043184399964957265,
"count": 1,
"is_parallel": true,
"self": 0.00043184399964957265
},
"communicator.exchange": {
"total": 0.039116965000175696,
"count": 1,
"is_parallel": true,
"self": 0.039116965000175696
},
"steps_from_proto": {
"total": 0.002308074000211491,
"count": 1,
"is_parallel": true,
"self": 0.0004188280004200351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018892459997914557,
"count": 10,
"is_parallel": true,
"self": 0.0018892459997914557
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.26548897600333,
"count": 18198,
"is_parallel": true,
"self": 11.27194237001504,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.87387071299554,
"count": 18198,
"is_parallel": true,
"self": 5.87387071299554
},
"communicator.exchange": {
"total": 191.46038124999814,
"count": 18198,
"is_parallel": true,
"self": 191.46038124999814
},
"steps_from_proto": {
"total": 36.65929464299461,
"count": 18198,
"is_parallel": true,
"self": 7.20672790603885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.45256673695576,
"count": 181980,
"is_parallel": true,
"self": 29.45256673695576
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012378899964460288,
"count": 1,
"self": 0.00012378899964460288,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 485.4555404789585,
"count": 718667,
"is_parallel": true,
"self": 15.235533327844223,
"children": {
"process_trajectory": {
"total": 271.7066568341147,
"count": 718667,
"is_parallel": true,
"self": 271.13195522311435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5747016110003642,
"count": 4,
"is_parallel": true,
"self": 0.5747016110003642
}
}
},
"_update_policy": {
"total": 198.51335031699955,
"count": 90,
"is_parallel": true,
"self": 64.9221657109897,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.59118460600985,
"count": 4587,
"is_parallel": true,
"self": 133.59118460600985
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08952757999986716,
"count": 1,
"self": 0.0009305879998464661,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08859699200002069,
"count": 1,
"self": 0.08859699200002069
}
}
}
}
}
}
}