ShuchengLi's picture
First Push trained snowball model
81da03b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0304111242294312,
"min": 1.0304111242294312,
"max": 2.860269546508789,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9827.03125,
"min": 9827.03125,
"max": 29292.01953125,
"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": 12.440984725952148,
"min": 0.42485466599464417,
"max": 12.440984725952148,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2425.991943359375,
"min": 82.42180633544922,
"max": 2526.1064453125,
"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": 0.06705056102067579,
"min": 0.06210441169598341,
"max": 0.07453848699112901,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26820224408270316,
"min": 0.24841764678393363,
"max": 0.3726924349556451,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21535716132790433,
"min": 0.1216628278626184,
"max": 0.2965710372024891,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8614286453116173,
"min": 0.4866513114504736,
"max": 1.3782205014836553,
"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": 24.386363636363637,
"min": 3.5,
"max": 24.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1073.0,
"min": 154.0,
"max": 1328.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.386363636363637,
"min": 3.5,
"max": 24.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1073.0,
"min": 154.0,
"max": 1328.0,
"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": "1758351993",
"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 --force --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1758352524"
},
"total": 530.8134283530001,
"count": 1,
"self": 0.4273584140000821,
"children": {
"run_training.setup": {
"total": 0.02434702000005018,
"count": 1,
"self": 0.02434702000005018
},
"TrainerController.start_learning": {
"total": 530.3617229189999,
"count": 1,
"self": 0.7332513039873447,
"children": {
"TrainerController._reset_env": {
"total": 1.952346979999902,
"count": 1,
"self": 1.952346979999902
},
"TrainerController.advance": {
"total": 527.5868375320131,
"count": 18200,
"self": 0.36126394103257553,
"children": {
"env_step": {
"total": 527.2255735909805,
"count": 18200,
"self": 334.88198266700056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 191.88169052699504,
"count": 18200,
"self": 1.8206509519868632,
"children": {
"TorchPolicy.evaluate": {
"total": 190.06103957500818,
"count": 18200,
"self": 190.06103957500818
}
}
},
"workers": {
"total": 0.4619003969849018,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 528.3341464279722,
"count": 18200,
"is_parallel": true,
"self": 264.4237396419762,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020867229998202674,
"count": 1,
"is_parallel": true,
"self": 0.0006243099999210244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001462412999899243,
"count": 10,
"is_parallel": true,
"self": 0.001462412999899243
}
}
},
"UnityEnvironment.step": {
"total": 0.038395174000015686,
"count": 1,
"is_parallel": true,
"self": 0.0005858370000169089,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004298080000353366,
"count": 1,
"is_parallel": true,
"self": 0.0004298080000353366
},
"communicator.exchange": {
"total": 0.03535979100001896,
"count": 1,
"is_parallel": true,
"self": 0.03535979100001896
},
"steps_from_proto": {
"total": 0.002019737999944482,
"count": 1,
"is_parallel": true,
"self": 0.000423541000145633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001596196999798849,
"count": 10,
"is_parallel": true,
"self": 0.001596196999798849
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 263.910406785996,
"count": 18199,
"is_parallel": true,
"self": 11.03979657598893,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.108454667992419,
"count": 18199,
"is_parallel": true,
"self": 6.108454667992419
},
"communicator.exchange": {
"total": 209.11836117700318,
"count": 18199,
"is_parallel": true,
"self": 209.11836117700318
},
"steps_from_proto": {
"total": 37.643794365011445,
"count": 18199,
"is_parallel": true,
"self": 7.292119576042751,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.351674788968694,
"count": 181990,
"is_parallel": true,
"self": 30.351674788968694
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001425269997525902,
"count": 1,
"self": 0.0001425269997525902,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 520.8304137907912,
"count": 837677,
"is_parallel": true,
"self": 17.293192742771907,
"children": {
"process_trajectory": {
"total": 292.719151076019,
"count": 837677,
"is_parallel": true,
"self": 292.12646439601895,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5926866800000425,
"count": 4,
"is_parallel": true,
"self": 0.5926866800000425
}
}
},
"_update_policy": {
"total": 210.81806997200033,
"count": 90,
"is_parallel": true,
"self": 59.28286187499771,
"children": {
"TorchPPOOptimizer.update": {
"total": 151.53520809700262,
"count": 4587,
"is_parallel": true,
"self": 151.53520809700262
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08914457599985326,
"count": 1,
"self": 0.0012174309995316435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08792714500032162,
"count": 1,
"self": 0.08792714500032162
}
}
}
}
}
}
}