OlejnikM's picture
First Push
74f7e80 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.5022602081298828,
"min": 1.5022602081298828,
"max": 2.8349201679229736,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 15467.2705078125,
"min": 15351.3232421875,
"max": 28938.865234375,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.337539672851562,
"min": 0.5177991986274719,
"max": 8.337539672851562,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1700.858154296875,
"min": 100.45304870605469,
"max": 1700.858154296875,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06643584113586329,
"min": 0.059157242598588455,
"max": 0.07375054838642017,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3321792056793164,
"min": 0.23662897039435382,
"max": 0.3645427834856616,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.26491491928988814,
"min": 0.14860686539631227,
"max": 0.27866546423996197,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.3245745964494406,
"min": 0.5944274615852491,
"max": 1.3933273211998098,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 17.89090909090909,
"min": 4.318181818181818,
"max": 17.89090909090909,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 984.0,
"min": 190.0,
"max": 984.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 17.89090909090909,
"min": 4.318181818181818,
"max": 17.89090909090909,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 984.0,
"min": 190.0,
"max": 984.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1774976632",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/envs/mlagagents_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1774976854"
},
"total": 222.39212270199982,
"count": 1,
"self": 0.43112549999955263,
"children": {
"run_training.setup": {
"total": 0.019144188000154827,
"count": 1,
"self": 0.019144188000154827
},
"TrainerController.start_learning": {
"total": 221.94185301400012,
"count": 1,
"self": 0.1617235859896482,
"children": {
"TrainerController._reset_env": {
"total": 2.5758988569998564,
"count": 1,
"self": 2.5758988569998564
},
"TrainerController.advance": {
"total": 219.1223074770105,
"count": 9128,
"self": 0.17215367099129253,
"children": {
"env_step": {
"total": 158.77502279600503,
"count": 9128,
"self": 124.54743731498002,
"children": {
"SubprocessEnvManager._take_step": {
"total": 34.128239301023086,
"count": 9128,
"self": 0.6157145250260783,
"children": {
"TorchPolicy.evaluate": {
"total": 33.51252477599701,
"count": 9128,
"self": 33.51252477599701
}
}
},
"workers": {
"total": 0.0993461800019304,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 220.84013189198868,
"count": 9128,
"is_parallel": true,
"self": 111.11328651598888,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019438110000464803,
"count": 1,
"is_parallel": true,
"self": 0.0005991620000713738,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013446489999751066,
"count": 10,
"is_parallel": true,
"self": 0.0013446489999751066
}
}
},
"UnityEnvironment.step": {
"total": 0.06966054900021845,
"count": 1,
"is_parallel": true,
"self": 0.0005618960001356754,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004064699999162258,
"count": 1,
"is_parallel": true,
"self": 0.0004064699999162258
},
"communicator.exchange": {
"total": 0.06485024200014777,
"count": 1,
"is_parallel": true,
"self": 0.06485024200014777
},
"steps_from_proto": {
"total": 0.003841941000018778,
"count": 1,
"is_parallel": true,
"self": 0.00033277200031989196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003509168999698886,
"count": 10,
"is_parallel": true,
"self": 0.003509168999698886
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 109.7268453759998,
"count": 9127,
"is_parallel": true,
"self": 5.172228144986548,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.693908988003386,
"count": 9127,
"is_parallel": true,
"self": 2.693908988003386
},
"communicator.exchange": {
"total": 83.26875971400955,
"count": 9127,
"is_parallel": true,
"self": 83.26875971400955
},
"steps_from_proto": {
"total": 18.59194852900032,
"count": 9127,
"is_parallel": true,
"self": 3.3743537390209895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.21759478997933,
"count": 91270,
"is_parallel": true,
"self": 15.21759478997933
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 60.175131010014184,
"count": 9128,
"self": 0.20222826102599356,
"children": {
"process_trajectory": {
"total": 13.45278677298893,
"count": 9128,
"self": 13.182463559988946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2703232129999833,
"count": 2,
"self": 0.2703232129999833
}
}
},
"_update_policy": {
"total": 46.52011597599926,
"count": 45,
"self": 19.366904741990083,
"children": {
"TorchPPOOptimizer.update": {
"total": 27.153211234009177,
"count": 2292,
"self": 27.153211234009177
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0539999948377954e-06,
"count": 1,
"self": 1.0539999948377954e-06
},
"TrainerController._save_models": {
"total": 0.08192204000010861,
"count": 1,
"self": 0.0010590900001261616,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08086294999998245,
"count": 1,
"self": 0.08086294999998245
}
}
}
}
}
}
}