Fangliuwh's picture
First Push
325ee90 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7702695727348328,
"min": 0.7565128207206726,
"max": 2.8450326919555664,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7320.64208984375,
"min": 7320.64208984375,
"max": 29042.09375,
"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": 13.177549362182617,
"min": 0.3391820788383484,
"max": 13.177549362182617,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2569.6220703125,
"min": 65.80132293701172,
"max": 2632.5498046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06667911791316561,
"min": 0.058412638306168344,
"max": 0.07456903763742566,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26671647165266243,
"min": 0.23365055322467337,
"max": 0.3728451881871283,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19026356906283134,
"min": 0.12977892911180344,
"max": 0.26878982314876476,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7610542762513254,
"min": 0.5191157164472138,
"max": 1.343949115743824,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.272727272727273,
"min": 4.0,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1156.0,
"min": 176.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.272727272727273,
"min": 4.0,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1156.0,
"min": 176.0,
"max": 1429.0,
"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": "1735419319",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=SnowballTarget4 --no-graphics --torch",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735419752"
},
"total": 432.825214533,
"count": 1,
"self": 0.4298508459999084,
"children": {
"run_training.setup": {
"total": 0.05842070800008514,
"count": 1,
"self": 0.05842070800008514
},
"TrainerController.start_learning": {
"total": 432.336942979,
"count": 1,
"self": 0.3527300339867452,
"children": {
"TrainerController._reset_env": {
"total": 1.9465137099998628,
"count": 1,
"self": 1.9465137099998628
},
"TrainerController.advance": {
"total": 429.9488062700134,
"count": 18192,
"self": 0.3745201929525592,
"children": {
"env_step": {
"total": 304.13094260801313,
"count": 18192,
"self": 231.29598171102862,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.61938979397632,
"count": 18192,
"self": 1.2862527379875246,
"children": {
"TorchPolicy.evaluate": {
"total": 71.3331370559888,
"count": 18192,
"self": 71.3331370559888
}
}
},
"workers": {
"total": 0.2155711030081875,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.88211291401535,
"count": 18192,
"is_parallel": true,
"self": 228.76206619301774,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022686240001803526,
"count": 1,
"is_parallel": true,
"self": 0.0006696150003335788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015990089998467738,
"count": 10,
"is_parallel": true,
"self": 0.0015990089998467738
}
}
},
"UnityEnvironment.step": {
"total": 0.03555960099993172,
"count": 1,
"is_parallel": true,
"self": 0.0006295469997894543,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044072900004721305,
"count": 1,
"is_parallel": true,
"self": 0.00044072900004721305
},
"communicator.exchange": {
"total": 0.03254953200007549,
"count": 1,
"is_parallel": true,
"self": 0.03254953200007549
},
"steps_from_proto": {
"total": 0.001939793000019563,
"count": 1,
"is_parallel": true,
"self": 0.00038576599945372436,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015540270005658385,
"count": 10,
"is_parallel": true,
"self": 0.0015540270005658385
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.1200467209976,
"count": 18191,
"is_parallel": true,
"self": 10.038197984019462,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.512988688996984,
"count": 18191,
"is_parallel": true,
"self": 5.512988688996984
},
"communicator.exchange": {
"total": 153.54863128899865,
"count": 18191,
"is_parallel": true,
"self": 153.54863128899865
},
"steps_from_proto": {
"total": 33.02022875898251,
"count": 18191,
"is_parallel": true,
"self": 5.967265303983595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.052963454998917,
"count": 181910,
"is_parallel": true,
"self": 27.052963454998917
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.4433434690477,
"count": 18192,
"self": 0.4080165960378963,
"children": {
"process_trajectory": {
"total": 29.096937869009935,
"count": 18192,
"self": 28.592955757009804,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5039821120001307,
"count": 4,
"self": 0.5039821120001307
}
}
},
"_update_policy": {
"total": 95.93838900399987,
"count": 90,
"self": 39.12581911100028,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.81256989299959,
"count": 4587,
"self": 56.81256989299959
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3630001376441214e-06,
"count": 1,
"self": 1.3630001376441214e-06
},
"TrainerController._save_models": {
"total": 0.088891601999876,
"count": 1,
"self": 0.0009018989999276528,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08798970299994835,
"count": 1,
"self": 0.08798970299994835
}
}
}
}
}
}
}