junruzhang's picture
First Push
2a3c129 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7886629104614258,
"min": 0.7807527780532837,
"max": 2.850423812866211,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7495.4521484375,
"min": 7495.4521484375,
"max": 29097.126953125,
"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": 12.694160461425781,
"min": 0.3475302755832672,
"max": 12.694160461425781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2475.361328125,
"min": 67.4208755493164,
"max": 2554.640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06526176021982204,
"min": 0.06154745906578861,
"max": 0.07568227905293873,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26104704087928815,
"min": 0.24618983626315444,
"max": 0.3717204321685987,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18948611507520957,
"min": 0.1266342540997464,
"max": 0.29666952503954663,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7579444603008383,
"min": 0.5065370163989856,
"max": 1.4053900943082922,
"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": 25.227272727272727,
"min": 3.8636363636363638,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 170.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.8636363636363638,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 170.0,
"max": 1381.0,
"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": "1757288751",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757289164"
},
"total": 412.8338260109999,
"count": 1,
"self": 0.7115447219999851,
"children": {
"run_training.setup": {
"total": 0.03042062600002282,
"count": 1,
"self": 0.03042062600002282
},
"TrainerController.start_learning": {
"total": 412.0918606629999,
"count": 1,
"self": 0.33481218100564547,
"children": {
"TrainerController._reset_env": {
"total": 2.742676799999913,
"count": 1,
"self": 2.742676799999913
},
"TrainerController.advance": {
"total": 408.89556969799446,
"count": 18192,
"self": 0.35434874798500005,
"children": {
"env_step": {
"total": 291.18636471200705,
"count": 18192,
"self": 224.3232514260037,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.65590945999759,
"count": 18192,
"self": 1.23552268498986,
"children": {
"TorchPolicy.evaluate": {
"total": 65.42038677500773,
"count": 18192,
"self": 65.42038677500773
}
}
},
"workers": {
"total": 0.2072038260057525,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 410.71527380102054,
"count": 18192,
"is_parallel": true,
"self": 213.75991615501516,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004591133999952035,
"count": 1,
"is_parallel": true,
"self": 0.00321967200011386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001371461999838175,
"count": 10,
"is_parallel": true,
"self": 0.001371461999838175
}
}
},
"UnityEnvironment.step": {
"total": 0.03443826000000172,
"count": 1,
"is_parallel": true,
"self": 0.0005691920000572281,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003955749999704494,
"count": 1,
"is_parallel": true,
"self": 0.0003955749999704494
},
"communicator.exchange": {
"total": 0.03168131999996149,
"count": 1,
"is_parallel": true,
"self": 0.03168131999996149
},
"steps_from_proto": {
"total": 0.0017921730000125535,
"count": 1,
"is_parallel": true,
"self": 0.0003575740000769656,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001434598999935588,
"count": 10,
"is_parallel": true,
"self": 0.001434598999935588
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 196.95535764600538,
"count": 18191,
"is_parallel": true,
"self": 9.660313723016998,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3127544699954115,
"count": 18191,
"is_parallel": true,
"self": 5.3127544699954115
},
"communicator.exchange": {
"total": 150.78354576599304,
"count": 18191,
"is_parallel": true,
"self": 150.78354576599304
},
"steps_from_proto": {
"total": 31.198743686999933,
"count": 18191,
"is_parallel": true,
"self": 5.482694704992923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.71604898200701,
"count": 181910,
"is_parallel": true,
"self": 25.71604898200701
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.35485623800241,
"count": 18192,
"self": 0.4109464330052788,
"children": {
"process_trajectory": {
"total": 26.663130466997814,
"count": 18192,
"self": 26.169077026997797,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49405344000001605,
"count": 4,
"self": 0.49405344000001605
}
}
},
"_update_policy": {
"total": 90.28077933799932,
"count": 90,
"self": 37.15762490399288,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.12315443400644,
"count": 4587,
"self": 53.12315443400644
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.323999867963721e-06,
"count": 1,
"self": 1.323999867963721e-06
},
"TrainerController._save_models": {
"total": 0.11880066000003353,
"count": 1,
"self": 0.0019934230001581454,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11680723699987539,
"count": 1,
"self": 0.11680723699987539
}
}
}
}
}
}
}