igabirondo13's picture
Upload folder using huggingface_hub
0c17566 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7261008024215698,
"min": 0.7261008024215698,
"max": 2.859611988067627,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6900.86181640625,
"min": 6900.86181640625,
"max": 29190.91796875,
"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": 12.717958450317383,
"min": 0.43635180592536926,
"max": 12.717958450317383,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2480.001953125,
"min": 84.65225219726562,
"max": 2576.932373046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06834005734708626,
"min": 0.06272303772246804,
"max": 0.07537342630031145,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27336022938834503,
"min": 0.2529172895683943,
"max": 0.35162885511332814,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19210751252431496,
"min": 0.12017167793865334,
"max": 0.28590842666579225,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7684300500972598,
"min": 0.48068671175461336,
"max": 1.4295421333289613,
"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": 25.318181818181817,
"min": 3.3181818181818183,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 146.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.3181818181818183,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 146.0,
"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": "1756730035",
"python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1756730463"
},
"total": 428.5054718210001,
"count": 1,
"self": 0.4264191160000337,
"children": {
"run_training.setup": {
"total": 0.020664807999992263,
"count": 1,
"self": 0.020664807999992263
},
"TrainerController.start_learning": {
"total": 428.0583878970001,
"count": 1,
"self": 0.39106063999315666,
"children": {
"TrainerController._reset_env": {
"total": 1.8311490790001699,
"count": 1,
"self": 1.8311490790001699
},
"TrainerController.advance": {
"total": 425.75594407900667,
"count": 18192,
"self": 0.40094321902165575,
"children": {
"env_step": {
"total": 305.6453442539844,
"count": 18192,
"self": 235.84233270897153,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.57333811200124,
"count": 18192,
"self": 1.2808299610205722,
"children": {
"TorchPolicy.evaluate": {
"total": 68.29250815098067,
"count": 18192,
"self": 68.29250815098067
}
}
},
"workers": {
"total": 0.22967343301161236,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.7014894949971,
"count": 18192,
"is_parallel": true,
"self": 220.46080624100227,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002005530000133149,
"count": 1,
"is_parallel": true,
"self": 0.0006371220001710753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013684079999620735,
"count": 10,
"is_parallel": true,
"self": 0.0013684079999620735
}
}
},
"UnityEnvironment.step": {
"total": 0.03453264900008435,
"count": 1,
"is_parallel": true,
"self": 0.0005628950000300392,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039778200016371557,
"count": 1,
"is_parallel": true,
"self": 0.00039778200016371557
},
"communicator.exchange": {
"total": 0.03171858499990776,
"count": 1,
"is_parallel": true,
"self": 0.03171858499990776
},
"steps_from_proto": {
"total": 0.0018533869999828312,
"count": 1,
"is_parallel": true,
"self": 0.00038818599978185375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014652010002009774,
"count": 10,
"is_parallel": true,
"self": 0.0014652010002009774
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.2406832539948,
"count": 18191,
"is_parallel": true,
"self": 9.77304121999532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.543990697010031,
"count": 18191,
"is_parallel": true,
"self": 5.543990697010031
},
"communicator.exchange": {
"total": 158.4557765239956,
"count": 18191,
"is_parallel": true,
"self": 158.4557765239956
},
"steps_from_proto": {
"total": 32.46787481299384,
"count": 18191,
"is_parallel": true,
"self": 5.821317911967981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.64655690102586,
"count": 181910,
"is_parallel": true,
"self": 26.64655690102586
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.70965660600064,
"count": 18192,
"self": 0.47017639100818087,
"children": {
"process_trajectory": {
"total": 26.10512885099206,
"count": 18192,
"self": 25.565840704991842,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5392881460002172,
"count": 4,
"self": 0.5392881460002172
}
}
},
"_update_policy": {
"total": 93.1343513640004,
"count": 90,
"self": 39.17966351999621,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.954687844004184,
"count": 4587,
"self": 53.954687844004184
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0150001799047459e-06,
"count": 1,
"self": 1.0150001799047459e-06
},
"TrainerController._save_models": {
"total": 0.08023308399992857,
"count": 1,
"self": 0.0009581409999555035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07927494299997306,
"count": 1,
"self": 0.07927494299997306
}
}
}
}
}
}
}