pdejong's picture
First Push
099f6d5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9525381326675415,
"min": 0.9525381326675415,
"max": 2.8738043308258057,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9094.833984375,
"min": 9094.833984375,
"max": 29462.2421875,
"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": 12.842252731323242,
"min": 0.22653314471244812,
"max": 12.842252731323242,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2504.2392578125,
"min": 43.94742965698242,
"max": 2599.7705078125,
"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": 0.06999430818470108,
"min": 0.0605607174944524,
"max": 0.0752791562648353,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2799772327388043,
"min": 0.2422428699778096,
"max": 0.3736411145815224,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21049478160692198,
"min": 0.136452888581427,
"max": 0.297923216048409,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8419791264276879,
"min": 0.545811554325708,
"max": 1.401581748735671,
"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": 25.704545454545453,
"min": 3.340909090909091,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 147.0,
"max": 1374.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.340909090909091,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 147.0,
"max": 1374.0,
"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": "1712942621",
"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": "1712943105"
},
"total": 484.01407420299984,
"count": 1,
"self": 0.49177213100006156,
"children": {
"run_training.setup": {
"total": 0.056788040999890654,
"count": 1,
"self": 0.056788040999890654
},
"TrainerController.start_learning": {
"total": 483.4655140309999,
"count": 1,
"self": 0.6435976709885836,
"children": {
"TrainerController._reset_env": {
"total": 2.662436157000002,
"count": 1,
"self": 2.662436157000002
},
"TrainerController.advance": {
"total": 480.0647235220115,
"count": 18199,
"self": 0.3181136500027151,
"children": {
"env_step": {
"total": 479.7466098720088,
"count": 18199,
"self": 310.837541399992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.57980438900245,
"count": 18199,
"self": 1.6448885170016183,
"children": {
"TorchPolicy.evaluate": {
"total": 166.93491587200083,
"count": 18199,
"self": 166.93491587200083
}
}
},
"workers": {
"total": 0.32926408301432275,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.2095446069984,
"count": 18199,
"is_parallel": true,
"self": 239.2253696810053,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005581818999871757,
"count": 1,
"is_parallel": true,
"self": 0.004044908000423675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015369109994480823,
"count": 10,
"is_parallel": true,
"self": 0.0015369109994480823
}
}
},
"UnityEnvironment.step": {
"total": 0.04031624100002773,
"count": 1,
"is_parallel": true,
"self": 0.0007388140002149157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042076399995494285,
"count": 1,
"is_parallel": true,
"self": 0.00042076399995494285
},
"communicator.exchange": {
"total": 0.036901381999996374,
"count": 1,
"is_parallel": true,
"self": 0.036901381999996374
},
"steps_from_proto": {
"total": 0.0022552809998614975,
"count": 1,
"is_parallel": true,
"self": 0.00042346300006101956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001831817999800478,
"count": 10,
"is_parallel": true,
"self": 0.001831817999800478
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.9841749259931,
"count": 18198,
"is_parallel": true,
"self": 11.154638351002177,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.027750194986083,
"count": 18198,
"is_parallel": true,
"self": 6.027750194986083
},
"communicator.exchange": {
"total": 187.84088755000516,
"count": 18198,
"is_parallel": true,
"self": 187.84088755000516
},
"steps_from_proto": {
"total": 37.96089882999968,
"count": 18198,
"is_parallel": true,
"self": 7.323747012935655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.637151817064023,
"count": 181980,
"is_parallel": true,
"self": 30.637151817064023
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019891399983862357,
"count": 1,
"self": 0.00019891399983862357,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 473.78931576290506,
"count": 729513,
"is_parallel": true,
"self": 15.935055109901896,
"children": {
"process_trajectory": {
"total": 264.34741520700163,
"count": 729513,
"is_parallel": true,
"self": 263.7113070490018,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6361081579998427,
"count": 4,
"is_parallel": true,
"self": 0.6361081579998427
}
}
},
"_update_policy": {
"total": 193.50684544600153,
"count": 90,
"is_parallel": true,
"self": 55.546787527011475,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.96005791899006,
"count": 4587,
"is_parallel": true,
"self": 137.96005791899006
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09455776699996932,
"count": 1,
"self": 0.0009991550000449934,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09355861199992432,
"count": 1,
"self": 0.09355861199992432
}
}
}
}
}
}
}