Jozaita's picture
First Push
1fee3aa verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9404668807983398,
"min": 0.9120275974273682,
"max": 2.845156669616699,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8938.197265625,
"min": 8938.197265625,
"max": 29043.359375,
"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": 12.890219688415527,
"min": 0.3355010151863098,
"max": 12.91264820098877,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2513.5927734375,
"min": 65.08719635009766,
"max": 2634.18017578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06731933550498284,
"min": 0.06306588445224014,
"max": 0.07466650715408227,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26927734201993136,
"min": 0.25570914507147346,
"max": 0.3706759155434602,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20265069618528964,
"min": 0.10273628877749776,
"max": 0.28168621557016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8106027847411585,
"min": 0.410945155109991,
"max": 1.333822901634609,
"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": 25.204545454545453,
"min": 3.090909090909091,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 136.0,
"max": 1398.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.090909090909091,
"max": 25.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 136.0,
"max": 1398.0,
"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": "1741864040",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741864516"
},
"total": 476.41681947700005,
"count": 1,
"self": 0.48791318700000375,
"children": {
"run_training.setup": {
"total": 0.02271393899997065,
"count": 1,
"self": 0.02271393899997065
},
"TrainerController.start_learning": {
"total": 475.9061923510001,
"count": 1,
"self": 0.4539683850009055,
"children": {
"TrainerController._reset_env": {
"total": 2.963181278000036,
"count": 1,
"self": 2.963181278000036
},
"TrainerController.advance": {
"total": 472.3902805629991,
"count": 18192,
"self": 0.4651806519866568,
"children": {
"env_step": {
"total": 342.34258620900846,
"count": 18192,
"self": 259.8296979500239,
"children": {
"SubprocessEnvManager._take_step": {
"total": 82.24252854399037,
"count": 18192,
"self": 1.4890652629916872,
"children": {
"TorchPolicy.evaluate": {
"total": 80.75346328099869,
"count": 18192,
"self": 80.75346328099869
}
}
},
"workers": {
"total": 0.27035971499418565,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.38316242599535,
"count": 18192,
"is_parallel": true,
"self": 247.66397990799408,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006137088000002677,
"count": 1,
"is_parallel": true,
"self": 0.004402318000018113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017347699999845645,
"count": 10,
"is_parallel": true,
"self": 0.0017347699999845645
}
}
},
"UnityEnvironment.step": {
"total": 0.036960502999988876,
"count": 1,
"is_parallel": true,
"self": 0.0006331769999974313,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004830290000086279,
"count": 1,
"is_parallel": true,
"self": 0.0004830290000086279
},
"communicator.exchange": {
"total": 0.03393344099998785,
"count": 1,
"is_parallel": true,
"self": 0.03393344099998785
},
"steps_from_proto": {
"total": 0.0019108559999949648,
"count": 1,
"is_parallel": true,
"self": 0.0003818579999688154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015289980000261494,
"count": 10,
"is_parallel": true,
"self": 0.0015289980000261494
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.71918251800128,
"count": 18191,
"is_parallel": true,
"self": 10.698930782002037,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.047627241997532,
"count": 18191,
"is_parallel": true,
"self": 6.047627241997532
},
"communicator.exchange": {
"total": 174.427375843998,
"count": 18191,
"is_parallel": true,
"self": 174.427375843998
},
"steps_from_proto": {
"total": 35.545248650003714,
"count": 18191,
"is_parallel": true,
"self": 6.769286059974206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.775962590029508,
"count": 181910,
"is_parallel": true,
"self": 28.775962590029508
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 129.582513702004,
"count": 18192,
"self": 0.5544069699971033,
"children": {
"process_trajectory": {
"total": 29.353247493006904,
"count": 18192,
"self": 28.890962761006847,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4622847320000574,
"count": 4,
"self": 0.4622847320000574
}
}
},
"_update_policy": {
"total": 99.674859239,
"count": 90,
"self": 39.591979154999194,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.082880084000806,
"count": 4587,
"self": 60.082880084000806
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1260000292168115e-06,
"count": 1,
"self": 1.1260000292168115e-06
},
"TrainerController._save_models": {
"total": 0.09876099899997826,
"count": 1,
"self": 0.0010536229999615898,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09770737600001667,
"count": 1,
"self": 0.09770737600001667
}
}
}
}
}
}
}