RTT's picture
First Push
b0ddad0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.14193856716156,
"min": 1.14193856716156,
"max": 2.8575448989868164,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10903.2294921875,
"min": 10903.2294921875,
"max": 29295.55078125,
"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": 11.901678085327148,
"min": 0.6101409792900085,
"max": 11.901678085327148,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2320.8271484375,
"min": 118.36735534667969,
"max": 2400.7041015625,
"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": 0.0687459402488814,
"min": 0.060209062053200244,
"max": 0.0747814369283422,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2749837609955256,
"min": 0.24083624821280097,
"max": 0.3699022966771451,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19745980520897052,
"min": 0.13358369153495148,
"max": 0.2846412971907971,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7898392208358821,
"min": 0.5343347661398059,
"max": 1.4232064859539855,
"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": 23.59090909090909,
"min": 4.068181818181818,
"max": 23.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1038.0,
"min": 179.0,
"max": 1288.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.59090909090909,
"min": 4.068181818181818,
"max": 23.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1038.0,
"min": 179.0,
"max": 1288.0,
"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": "1710774383",
"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": "1710774884"
},
"total": 501.442462889,
"count": 1,
"self": 0.43421136699998897,
"children": {
"run_training.setup": {
"total": 0.05638238900007764,
"count": 1,
"self": 0.05638238900007764
},
"TrainerController.start_learning": {
"total": 500.95186913299995,
"count": 1,
"self": 0.6690434819872735,
"children": {
"TrainerController._reset_env": {
"total": 2.8839766059999192,
"count": 1,
"self": 2.8839766059999192
},
"TrainerController.advance": {
"total": 497.2910340120128,
"count": 18200,
"self": 0.3398465800097483,
"children": {
"env_step": {
"total": 496.95118743200305,
"count": 18200,
"self": 322.6533308320305,
"children": {
"SubprocessEnvManager._take_step": {
"total": 173.95318624597985,
"count": 18200,
"self": 1.7293137419783307,
"children": {
"TorchPolicy.evaluate": {
"total": 172.22387250400152,
"count": 18200,
"self": 172.22387250400152
}
}
},
"workers": {
"total": 0.344670353992683,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 499.43648304800627,
"count": 18200,
"is_parallel": true,
"self": 245.48988994801584,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005940184999985831,
"count": 1,
"is_parallel": true,
"self": 0.004151612999748977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017885720002368544,
"count": 10,
"is_parallel": true,
"self": 0.0017885720002368544
}
}
},
"UnityEnvironment.step": {
"total": 0.05832139400001779,
"count": 1,
"is_parallel": true,
"self": 0.0007623449999982768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046609999992597295,
"count": 1,
"is_parallel": true,
"self": 0.00046609999992597295
},
"communicator.exchange": {
"total": 0.054859476000046925,
"count": 1,
"is_parallel": true,
"self": 0.054859476000046925
},
"steps_from_proto": {
"total": 0.002233473000046615,
"count": 1,
"is_parallel": true,
"self": 0.00036976900003082847,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018637040000157867,
"count": 10,
"is_parallel": true,
"self": 0.0018637040000157867
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.94659309999042,
"count": 18199,
"is_parallel": true,
"self": 11.462951702959117,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.180879928018271,
"count": 18199,
"is_parallel": true,
"self": 6.180879928018271
},
"communicator.exchange": {
"total": 197.73113832501042,
"count": 18199,
"is_parallel": true,
"self": 197.73113832501042
},
"steps_from_proto": {
"total": 38.571623144002615,
"count": 18199,
"is_parallel": true,
"self": 7.476395562934158,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.095227581068457,
"count": 181990,
"is_parallel": true,
"self": 31.095227581068457
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.306200003156846e-05,
"count": 1,
"self": 4.306200003156846e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 490.9815700609802,
"count": 752717,
"is_parallel": true,
"self": 16.685028122011886,
"children": {
"process_trajectory": {
"total": 273.59200762896785,
"count": 752717,
"is_parallel": true,
"self": 272.7633742929679,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8286333359999389,
"count": 4,
"is_parallel": true,
"self": 0.8286333359999389
}
}
},
"_update_policy": {
"total": 200.70453431000044,
"count": 90,
"is_parallel": true,
"self": 55.234715012004926,
"children": {
"TorchPPOOptimizer.update": {
"total": 145.4698192979955,
"count": 4587,
"is_parallel": true,
"self": 145.4698192979955
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10777197099992009,
"count": 1,
"self": 0.0011140639999211999,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10665790699999889,
"count": 1,
"self": 0.10665790699999889
}
}
}
}
}
}
}