snowball-v1 / run_logs /timers.json
Aryan2050's picture
messgae=First Snowball
654ae4e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8128258585929871,
"min": 0.8128258585929871,
"max": 2.868042469024658,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7725.0966796875,
"min": 7725.0966796875,
"max": 29276.9765625,
"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": 13.301617622375488,
"min": 0.38718271255493164,
"max": 13.411689758300781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2593.8154296875,
"min": 75.11344909667969,
"max": 2735.984619140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07061407794061975,
"min": 0.06363473003661699,
"max": 0.07603432085563647,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.282456311762479,
"min": 0.26093960190865245,
"max": 0.38017160427818236,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19389863808949787,
"min": 0.11503329233827947,
"max": 0.30077675814722105,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7755945523579915,
"min": 0.4601331693531179,
"max": 1.5038837907361051,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.818181818181817,
"min": 3.3181818181818183,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 146.0,
"max": 1434.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.3181818181818183,
"max": 26.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 146.0,
"max": 1434.0,
"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": "1751656518",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751656945"
},
"total": 426.55690434999997,
"count": 1,
"self": 0.4383716329998606,
"children": {
"run_training.setup": {
"total": 0.023554152000087925,
"count": 1,
"self": 0.023554152000087925
},
"TrainerController.start_learning": {
"total": 426.094978565,
"count": 1,
"self": 0.36848731199461326,
"children": {
"TrainerController._reset_env": {
"total": 3.22689840299995,
"count": 1,
"self": 3.22689840299995
},
"TrainerController.advance": {
"total": 422.42057968300537,
"count": 18192,
"self": 0.37714328698962163,
"children": {
"env_step": {
"total": 303.9445053650072,
"count": 18192,
"self": 233.73307773300826,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.0067614709942,
"count": 18192,
"self": 1.2439915939989987,
"children": {
"TorchPolicy.evaluate": {
"total": 68.76276987699521,
"count": 18192,
"self": 68.76276987699521
}
}
},
"workers": {
"total": 0.2046661610047522,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.1594580460044,
"count": 18192,
"is_parallel": true,
"self": 219.6189069459981,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005621478999955798,
"count": 1,
"is_parallel": true,
"self": 0.004194930999801727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001426548000154071,
"count": 10,
"is_parallel": true,
"self": 0.001426548000154071
}
}
},
"UnityEnvironment.step": {
"total": 0.03715171199996803,
"count": 1,
"is_parallel": true,
"self": 0.0008230220000768895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004193380000288016,
"count": 1,
"is_parallel": true,
"self": 0.0004193380000288016
},
"communicator.exchange": {
"total": 0.033986354000035135,
"count": 1,
"is_parallel": true,
"self": 0.033986354000035135
},
"steps_from_proto": {
"total": 0.0019229979998272029,
"count": 1,
"is_parallel": true,
"self": 0.000357933999339366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001565064000487837,
"count": 10,
"is_parallel": true,
"self": 0.001565064000487837
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.54055110000627,
"count": 18191,
"is_parallel": true,
"self": 9.800782387987283,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.452358136015846,
"count": 18191,
"is_parallel": true,
"self": 5.452358136015846
},
"communicator.exchange": {
"total": 157.6084107310005,
"count": 18191,
"is_parallel": true,
"self": 157.6084107310005
},
"steps_from_proto": {
"total": 31.678999845002636,
"count": 18191,
"is_parallel": true,
"self": 5.782366586942771,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.896633258059865,
"count": 181910,
"is_parallel": true,
"self": 25.896633258059865
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.09893103100853,
"count": 18192,
"self": 0.4371469690183858,
"children": {
"process_trajectory": {
"total": 26.677448957989554,
"count": 18192,
"self": 26.272655651989226,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4047933060003288,
"count": 4,
"self": 0.4047933060003288
}
}
},
"_update_policy": {
"total": 90.98433510400059,
"count": 90,
"self": 37.41825967899058,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.56607542501001,
"count": 4587,
"self": 53.56607542501001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.870000212686136e-07,
"count": 1,
"self": 9.870000212686136e-07
},
"TrainerController._save_models": {
"total": 0.07901218000006338,
"count": 1,
"self": 0.0007784800000081304,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07823370000005525,
"count": 1,
"self": 0.07823370000005525
}
}
}
}
}
}
}