TPK-MAKG's picture
Initial Push
e223dd2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9951054453849792,
"min": 0.9809223413467407,
"max": 2.869385004043579,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9512.212890625,
"min": 9512.212890625,
"max": 29416.935546875,
"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": 12.77269458770752,
"min": 0.3009917140007019,
"max": 12.77269458770752,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2490.675537109375,
"min": 58.392391204833984,
"max": 2604.87841796875,
"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": 25.045454545454547,
"min": 3.409090909090909,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 150.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.409090909090909,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 150.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07404895963126738,
"min": 0.06178543628330398,
"max": 0.07710157463877883,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29619583852506953,
"min": 0.2517605883921908,
"max": 0.36638509627008203,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2167278680146909,
"min": 0.11153923374299399,
"max": 0.27711010733071495,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8669114720587636,
"min": 0.44615693497197595,
"max": 1.3855505366535747,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029184900271699997,
"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": 0.19728300000000004,
"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": 0.0048644217,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"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": "1729876640",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729877183"
},
"total": 543.341416793,
"count": 1,
"self": 0.5418193360000032,
"children": {
"run_training.setup": {
"total": 0.10157239900001969,
"count": 1,
"self": 0.10157239900001969
},
"TrainerController.start_learning": {
"total": 542.698025058,
"count": 1,
"self": 0.7795575909992749,
"children": {
"TrainerController._reset_env": {
"total": 6.031847185000004,
"count": 1,
"self": 6.031847185000004
},
"TrainerController.advance": {
"total": 535.8039644410007,
"count": 18202,
"self": 0.3802335349982968,
"children": {
"env_step": {
"total": 535.4237309060024,
"count": 18202,
"self": 414.27198855299815,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.75312195199808,
"count": 18202,
"self": 1.8873475679907301,
"children": {
"TorchPolicy.evaluate": {
"total": 118.86577438400735,
"count": 18202,
"self": 118.86577438400735
}
}
},
"workers": {
"total": 0.39862040100621243,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 540.9835122900081,
"count": 18202,
"is_parallel": true,
"self": 253.55968253801376,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0036551470000176778,
"count": 1,
"is_parallel": true,
"self": 0.0009124060000544887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002742740999963189,
"count": 10,
"is_parallel": true,
"self": 0.002742740999963189
}
}
},
"UnityEnvironment.step": {
"total": 0.04279295800000682,
"count": 1,
"is_parallel": true,
"self": 0.0008374209999715276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043739900002037757,
"count": 1,
"is_parallel": true,
"self": 0.00043739900002037757
},
"communicator.exchange": {
"total": 0.03919001899998875,
"count": 1,
"is_parallel": true,
"self": 0.03919001899998875
},
"steps_from_proto": {
"total": 0.002328119000026163,
"count": 1,
"is_parallel": true,
"self": 0.00043333000013490164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018947889998912615,
"count": 10,
"is_parallel": true,
"self": 0.0018947889998912615
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 287.42382975199433,
"count": 18201,
"is_parallel": true,
"self": 13.422744065998927,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.9079578320007045,
"count": 18201,
"is_parallel": true,
"self": 6.9079578320007045
},
"communicator.exchange": {
"total": 224.82167861699156,
"count": 18201,
"is_parallel": true,
"self": 224.82167861699156
},
"steps_from_proto": {
"total": 42.27144923700314,
"count": 18201,
"is_parallel": true,
"self": 8.306320778998327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.96512845800481,
"count": 182010,
"is_parallel": true,
"self": 33.96512845800481
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002051049999636234,
"count": 1,
"self": 0.0002051049999636234,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 529.7882259339457,
"count": 708984,
"is_parallel": true,
"self": 15.610888970938618,
"children": {
"process_trajectory": {
"total": 283.00400341500745,
"count": 708984,
"is_parallel": true,
"self": 282.31408113700746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6899222779999832,
"count": 4,
"is_parallel": true,
"self": 0.6899222779999832
}
}
},
"_update_policy": {
"total": 231.17333354799968,
"count": 90,
"is_parallel": true,
"self": 69.12355800800111,
"children": {
"TorchPPOOptimizer.update": {
"total": 162.04977553999856,
"count": 4584,
"is_parallel": true,
"self": 162.04977553999856
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08245073599994157,
"count": 1,
"self": 0.0011617989998740086,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08128893700006756,
"count": 1,
"self": 0.08128893700006756
}
}
}
}
}
}
}