jaruiz's picture
First model
d4c7cd5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7814210057258606,
"min": 0.7814210057258606,
"max": 2.8278863430023193,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7426.62548828125,
"min": 7426.62548828125,
"max": 26663.3984375,
"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": 12.917593002319336,
"min": 0.5255940556526184,
"max": 12.917593002319336,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.9306640625,
"min": 78.839111328125,
"max": 2609.436279296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06797471578694039,
"min": 0.06376240804538078,
"max": 0.07189620674325495,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27189886314776157,
"min": 0.2107818677173675,
"max": 0.35935734733357094,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20024946594939513,
"min": 0.16242339921311713,
"max": 0.2782951169154223,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8009978637975805,
"min": 0.4872701976393514,
"max": 1.3914755845771116,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000290232003256,
"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": 0.19674400000000003,
"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": 0.0048375256,
"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": 6567.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.363636363636363,
"min": 4.484848484848484,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 148.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 4.484848484848484,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 148.0,
"max": 1414.0,
"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": "1756735124",
"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 --resume",
"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": "1756735684"
},
"total": 560.3972432090001,
"count": 1,
"self": 0.5851064420000966,
"children": {
"run_training.setup": {
"total": 0.04191491599999608,
"count": 1,
"self": 0.04191491599999608
},
"TrainerController.start_learning": {
"total": 559.770221851,
"count": 1,
"self": 0.6138170450086591,
"children": {
"TrainerController._reset_env": {
"total": 2.8120547219999708,
"count": 1,
"self": 2.8120547219999708
},
"TrainerController.advance": {
"total": 556.2707212119911,
"count": 17992,
"self": 0.642549939003402,
"children": {
"env_step": {
"total": 390.8550183809974,
"count": 17992,
"self": 334.08714140200436,
"children": {
"SubprocessEnvManager._take_step": {
"total": 56.38295893499344,
"count": 17992,
"self": 2.0764429319982582,
"children": {
"TorchPolicy.evaluate": {
"total": 54.30651600299518,
"count": 17992,
"self": 54.30651600299518
}
}
},
"workers": {
"total": 0.38491804399961893,
"count": 17992,
"self": 0.0,
"children": {
"worker_root": {
"total": 557.6020717770168,
"count": 17992,
"is_parallel": true,
"self": 268.7882789560241,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003851951999990888,
"count": 1,
"is_parallel": true,
"self": 0.0013256219998538654,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025263300001370226,
"count": 10,
"is_parallel": true,
"self": 0.0025263300001370226
}
}
},
"UnityEnvironment.step": {
"total": 0.0479895180000085,
"count": 1,
"is_parallel": true,
"self": 0.000735283000039999,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004949729999452757,
"count": 1,
"is_parallel": true,
"self": 0.0004949729999452757
},
"communicator.exchange": {
"total": 0.04458745700003419,
"count": 1,
"is_parallel": true,
"self": 0.04458745700003419
},
"steps_from_proto": {
"total": 0.0021718049999890354,
"count": 1,
"is_parallel": true,
"self": 0.0004399160000048141,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017318889999842213,
"count": 10,
"is_parallel": true,
"self": 0.0017318889999842213
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 288.8137928209927,
"count": 17991,
"is_parallel": true,
"self": 13.481699612976513,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.362628993006751,
"count": 17991,
"is_parallel": true,
"self": 7.362628993006751
},
"communicator.exchange": {
"total": 227.1775076609997,
"count": 17991,
"is_parallel": true,
"self": 227.1775076609997
},
"steps_from_proto": {
"total": 40.791956554009744,
"count": 17991,
"is_parallel": true,
"self": 7.763809556949809,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.028146997059935,
"count": 179910,
"is_parallel": true,
"self": 33.028146997059935
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 164.77315289199032,
"count": 17992,
"self": 0.8052786280067039,
"children": {
"process_trajectory": {
"total": 31.418337295984088,
"count": 17992,
"self": 30.836450417984224,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5818868779998638,
"count": 4,
"self": 0.5818868779998638
}
}
},
"_update_policy": {
"total": 132.54953696799953,
"count": 89,
"self": 47.969427773997495,
"children": {
"TorchPPOOptimizer.update": {
"total": 84.58010919400203,
"count": 4536,
"self": 84.58010919400203
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0570001904852688e-06,
"count": 1,
"self": 1.0570001904852688e-06
},
"TrainerController._save_models": {
"total": 0.07362781500000892,
"count": 1,
"self": 0.002062608999949589,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07156520600005933,
"count": 1,
"self": 0.07156520600005933
}
}
}
}
}
}
}