byfengwu's picture
First Push
ad4d0d2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9476588368415833,
"min": 0.9473971128463745,
"max": 2.827476739883423,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9006.5498046875,
"min": 9006.5498046875,
"max": 28862.8828125,
"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": 12.02534008026123,
"min": 0.4024864137172699,
"max": 12.02534008026123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2344.94140625,
"min": 78.08236694335938,
"max": 2424.51904296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06732845620678621,
"min": 0.060337600276826005,
"max": 0.07665276413243584,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26931382482714483,
"min": 0.24135040110730402,
"max": 0.36281541069083867,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20387081758064382,
"min": 0.1358710084961928,
"max": 0.27533313785405716,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8154832703225753,
"min": 0.5434840339847712,
"max": 1.2907533081723195,
"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": 23.795454545454547,
"min": 3.227272727272727,
"max": 23.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1047.0,
"min": 142.0,
"max": 1271.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.795454545454547,
"min": 3.227272727272727,
"max": 23.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1047.0,
"min": 142.0,
"max": 1271.0,
"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": "1777974116",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"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": "1777974591"
},
"total": 474.566383847,
"count": 1,
"self": 0.4834234700001616,
"children": {
"run_training.setup": {
"total": 0.02700582499983284,
"count": 1,
"self": 0.02700582499983284
},
"TrainerController.start_learning": {
"total": 474.055954552,
"count": 1,
"self": 0.42614270098556517,
"children": {
"TrainerController._reset_env": {
"total": 3.258015984999929,
"count": 1,
"self": 3.258015984999929
},
"TrainerController.advance": {
"total": 470.2912310030147,
"count": 18192,
"self": 0.43143699002689573,
"children": {
"env_step": {
"total": 342.673843478997,
"count": 18192,
"self": 265.4326973299717,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.99555055901897,
"count": 18192,
"self": 1.3980525890219724,
"children": {
"TorchPolicy.evaluate": {
"total": 75.597497969997,
"count": 18192,
"self": 75.597497969997
}
}
},
"workers": {
"total": 0.24559559000636,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.2407024960055,
"count": 18192,
"is_parallel": true,
"self": 240.1246171360158,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004395901999941998,
"count": 1,
"is_parallel": true,
"self": 0.0030559089998405398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013399930001014582,
"count": 10,
"is_parallel": true,
"self": 0.0013399930001014582
}
}
},
"UnityEnvironment.step": {
"total": 0.0371842160000142,
"count": 1,
"is_parallel": true,
"self": 0.0006975230003263277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044638099984695145,
"count": 1,
"is_parallel": true,
"self": 0.00044638099984695145
},
"communicator.exchange": {
"total": 0.03368340099996203,
"count": 1,
"is_parallel": true,
"self": 0.03368340099996203
},
"steps_from_proto": {
"total": 0.0023569109998788917,
"count": 1,
"is_parallel": true,
"self": 0.00046562699981222977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001891284000066662,
"count": 10,
"is_parallel": true,
"self": 0.001891284000066662
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.1160853599897,
"count": 18191,
"is_parallel": true,
"self": 10.71805155799916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.796521700990979,
"count": 18191,
"is_parallel": true,
"self": 5.796521700990979
},
"communicator.exchange": {
"total": 176.50556602198276,
"count": 18191,
"is_parallel": true,
"self": 176.50556602198276
},
"steps_from_proto": {
"total": 39.09594607901681,
"count": 18191,
"is_parallel": true,
"self": 6.961498372000051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.13444770701676,
"count": 181910,
"is_parallel": true,
"self": 32.13444770701676
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.18595053399076,
"count": 18192,
"self": 0.5425558589888624,
"children": {
"process_trajectory": {
"total": 28.026655043001483,
"count": 18192,
"self": 27.579495239001517,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44715980399996624,
"count": 4,
"self": 0.44715980399996624
}
}
},
"_update_policy": {
"total": 98.61673963200042,
"count": 90,
"self": 40.20500799399542,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.411731638004994,
"count": 4587,
"self": 58.411731638004994
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.503000021330081e-06,
"count": 1,
"self": 1.503000021330081e-06
},
"TrainerController._save_models": {
"total": 0.08056335999981457,
"count": 1,
"self": 0.0007189929997366562,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07984436700007791,
"count": 1,
"self": 0.07984436700007791
}
}
}
}
}
}
}