atom-mu-control's picture
First Push
d749ed3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.713909924030304,
"min": 0.703331470489502,
"max": 2.8689637184143066,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7256.1806640625,
"min": 6800.51171875,
"max": 29349.5,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 399992.0,
"min": 9952.0,
"max": 399992.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.708879470825195,
"min": 0.3584410548210144,
"max": 13.708879470825195,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2673.2314453125,
"min": 69.53756713867188,
"max": 2805.201904296875,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06470135551807128,
"min": 0.06404164398965591,
"max": 0.0745097869535785,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25880542207228513,
"min": 0.2578275439765414,
"max": 0.36955259602468954,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16590489628998673,
"min": 0.11440360684509335,
"max": 0.26670169429305723,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6636195851599469,
"min": 0.4576144273803734,
"max": 1.333508471465286,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.297098702999998e-06,
"min": 1.297098702999998e-06,
"max": 9.864700135300001e-05,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.188394811999992e-06,
"min": 5.188394811999992e-06,
"max": 0.00048086001914000013,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10129700000000001,
"min": 0.10129700000000001,
"max": 0.198647,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40518800000000005,
"min": 0.40518800000000005,
"max": 0.9808600000000002,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.472029999999993e-05,
"min": 7.472029999999993e-05,
"max": 0.0049324853,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002988811999999997,
"min": 0.0002988811999999997,
"max": 0.024044913999999997,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.15909090909091,
"min": 3.7954545454545454,
"max": 27.15909090909091,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1195.0,
"min": 167.0,
"max": 1491.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.15909090909091,
"min": 3.7954545454545454,
"max": 27.15909090909091,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1195.0,
"min": 167.0,
"max": 1491.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1706524409",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706525404"
},
"total": 995.692103045,
"count": 1,
"self": 0.48681451399988873,
"children": {
"run_training.setup": {
"total": 0.05822579499999847,
"count": 1,
"self": 0.05822579499999847
},
"TrainerController.start_learning": {
"total": 995.1470627360001,
"count": 1,
"self": 1.1194683749778278,
"children": {
"TrainerController._reset_env": {
"total": 3.2258184840000013,
"count": 1,
"self": 3.2258184840000013
},
"TrainerController.advance": {
"total": 990.6435928390222,
"count": 36399,
"self": 0.5161438230067006,
"children": {
"env_step": {
"total": 990.1274490160155,
"count": 36399,
"self": 685.9821636899762,
"children": {
"SubprocessEnvManager._take_step": {
"total": 303.6058591870004,
"count": 36399,
"self": 2.8179177320072313,
"children": {
"TorchPolicy.evaluate": {
"total": 300.7879414549932,
"count": 36399,
"self": 300.7879414549932
}
}
},
"workers": {
"total": 0.5394261390388237,
"count": 36399,
"self": 0.0,
"children": {
"worker_root": {
"total": 992.7601482400158,
"count": 36399,
"is_parallel": true,
"self": 556.4008363560199,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005326202999981433,
"count": 1,
"is_parallel": true,
"self": 0.003934920000006059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001391282999975374,
"count": 10,
"is_parallel": true,
"self": 0.001391282999975374
}
}
},
"UnityEnvironment.step": {
"total": 0.03677558399999725,
"count": 1,
"is_parallel": true,
"self": 0.0006664109998837375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038737700003821374,
"count": 1,
"is_parallel": true,
"self": 0.00038737700003821374
},
"communicator.exchange": {
"total": 0.03349099800004751,
"count": 1,
"is_parallel": true,
"self": 0.03349099800004751
},
"steps_from_proto": {
"total": 0.0022307980000277894,
"count": 1,
"is_parallel": true,
"self": 0.00040905799994561676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018217400000821726,
"count": 10,
"is_parallel": true,
"self": 0.0018217400000821726
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 436.35931188399593,
"count": 36398,
"is_parallel": true,
"self": 20.950862612960464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.308775385004765,
"count": 36398,
"is_parallel": true,
"self": 10.308775385004765
},
"communicator.exchange": {
"total": 339.9539179130245,
"count": 36398,
"is_parallel": true,
"self": 339.9539179130245
},
"steps_from_proto": {
"total": 65.1457559730062,
"count": 36398,
"is_parallel": true,
"self": 11.932008319043348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.213747653962855,
"count": 363980,
"is_parallel": true,
"self": 53.213747653962855
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002733460000854393,
"count": 1,
"self": 0.0002733460000854393,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 980.0479222058372,
"count": 1308761,
"is_parallel": true,
"self": 27.6382944246252,
"children": {
"process_trajectory": {
"total": 473.0913014762108,
"count": 1308761,
"is_parallel": true,
"self": 471.0166283852104,
"children": {
"RLTrainer._checkpoint": {
"total": 2.0746730910003635,
"count": 8,
"is_parallel": true,
"self": 2.0746730910003635
}
}
},
"_update_policy": {
"total": 479.31832630500116,
"count": 181,
"is_parallel": true,
"self": 159.07569045900243,
"children": {
"TorchPPOOptimizer.update": {
"total": 320.24263584599873,
"count": 15375,
"is_parallel": true,
"self": 320.24263584599873
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15790969199997562,
"count": 1,
"self": 0.0022610199998780445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15564867200009758,
"count": 1,
"self": 0.15564867200009758
}
}
}
}
}
}
}