propet's picture
snowball version 2
8d2e964
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.7194676399230957,
"min": 1.7135539054870605,
"max": 2.817811965942383,
"count": 80
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 18592.603515625,
"min": 11489.958984375,
"max": 31119.916015625,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 6567.0,
"max": 13134.0,
"count": 80
},
"SnowballTarget.Step.mean": {
"value": 999800.0,
"min": 209800.0,
"max": 999800.0,
"count": 80
},
"SnowballTarget.Step.sum": {
"value": 999800.0,
"min": 209800.0,
"max": 999800.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 7.987432956695557,
"min": 0.8157598972320557,
"max": 7.996119499206543,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 399.37164306640625,
"min": 39.15647506713867,
"max": 399.80596923828125,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 19.88,
"min": 5.82,
"max": 20.42,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 994.0,
"min": 285.0,
"max": 1021.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.88,
"min": 5.82,
"max": 20.42,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 994.0,
"min": 285.0,
"max": 1021.0,
"count": 80
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03535417499336957,
"min": 0.03159011911180506,
"max": 0.0384297544189555,
"count": 15
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03535417499336957,
"min": 0.03159011911180506,
"max": 0.0384297544189555,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.28228020916382474,
"min": 0.22182851791584574,
"max": 0.2915855326822826,
"count": 15
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.28228020916382474,
"min": 0.22182851791584574,
"max": 0.2915855326822826,
"count": 15
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.0800959199999955e-06,
"min": 4.0800959199999955e-06,
"max": 7.492002507999999e-05,
"count": 15
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.0800959199999955e-06,
"min": 4.0800959199999955e-06,
"max": 7.492002507999999e-05,
"count": 15
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10407999999999996,
"min": 0.10407999999999996,
"max": 0.17492,
"count": 15
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10407999999999996,
"min": 0.10407999999999996,
"max": 0.17492,
"count": 15
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00021359199999999978,
"min": 0.00021359199999999978,
"max": 0.0037485080000000007,
"count": 15
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00021359199999999978,
"min": 0.00021359199999999978,
"max": 0.0037485080000000007,
"count": 15
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678967802",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"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": "1678969730"
},
"total": 1928.2197429819998,
"count": 1,
"self": 0.43751327599966316,
"children": {
"run_training.setup": {
"total": 0.12351631000001362,
"count": 1,
"self": 0.12351631000001362
},
"TrainerController.start_learning": {
"total": 1927.6587133960002,
"count": 1,
"self": 2.532124646015518,
"children": {
"TrainerController._reset_env": {
"total": 5.70910750500002,
"count": 1,
"self": 5.70910750500002
},
"TrainerController.advance": {
"total": 1919.2670988659847,
"count": 72813,
"self": 1.2786658340266968,
"children": {
"env_step": {
"total": 1917.988433031958,
"count": 72813,
"self": 1420.739594100971,
"children": {
"SubprocessEnvManager._take_step": {
"total": 495.9592163650191,
"count": 72813,
"self": 9.976391652053508,
"children": {
"TorchPolicy.evaluate": {
"total": 485.98282471296557,
"count": 72813,
"self": 485.98282471296557
}
}
},
"workers": {
"total": 1.2896225659678748,
"count": 72813,
"self": 0.0,
"children": {
"worker_root": {
"total": 1920.9545797070616,
"count": 72813,
"is_parallel": true,
"self": 872.6664106290941,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002129897000031633,
"count": 1,
"is_parallel": true,
"self": 0.0007336999995004589,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013961970005311741,
"count": 10,
"is_parallel": true,
"self": 0.0013961970005311741
}
}
},
"UnityEnvironment.step": {
"total": 0.11478298200017889,
"count": 1,
"is_parallel": true,
"self": 0.0005654100004903739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040915699992183363,
"count": 1,
"is_parallel": true,
"self": 0.00040915699992183363
},
"communicator.exchange": {
"total": 0.11178061099985825,
"count": 1,
"is_parallel": true,
"self": 0.11178061099985825
},
"steps_from_proto": {
"total": 0.0020278039999084285,
"count": 1,
"is_parallel": true,
"self": 0.0004553339997528383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015724700001555902,
"count": 10,
"is_parallel": true,
"self": 0.0015724700001555902
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1048.2881690779675,
"count": 72812,
"is_parallel": true,
"self": 39.78568954113166,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.221257442967726,
"count": 72812,
"is_parallel": true,
"self": 22.221257442967726
},
"communicator.exchange": {
"total": 848.9218138739884,
"count": 72812,
"is_parallel": true,
"self": 848.9218138739884
},
"steps_from_proto": {
"total": 137.3594082198797,
"count": 72812,
"is_parallel": true,
"self": 27.91487495593583,
"children": {
"_process_rank_one_or_two_observation": {
"total": 109.44453326394387,
"count": 728120,
"is_parallel": true,
"self": 109.44453326394387
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0007958520000101998,
"count": 1,
"self": 0.0007958520000101998,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1894.1888671859158,
"count": 2769056,
"is_parallel": true,
"self": 68.69717191070777,
"children": {
"process_trajectory": {
"total": 1457.1347984322076,
"count": 2769056,
"is_parallel": true,
"self": 1450.333885229207,
"children": {
"RLTrainer._checkpoint": {
"total": 6.8009132030006185,
"count": 16,
"is_parallel": true,
"self": 6.8009132030006185
}
}
},
"_update_policy": {
"total": 368.3568968430004,
"count": 15,
"is_parallel": true,
"self": 232.81525939297285,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.54163745002757,
"count": 4410,
"is_parallel": true,
"self": 135.54163745002757
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14958652699988306,
"count": 1,
"self": 0.0014586749998670712,
"children": {
"RLTrainer._checkpoint": {
"total": 0.148127852000016,
"count": 1,
"self": 0.148127852000016
}
}
}
}
}
}
}