Monadillo's picture
First Push
1b6cef9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6334779262542725,
"min": 0.6207982301712036,
"max": 0.9066750407218933,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6466.54296875,
"min": 5900.06640625,
"max": 9335.1259765625,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 599976.0,
"min": 209936.0,
"max": 599976.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 599976.0,
"min": 209936.0,
"max": 599976.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.873224258422852,
"min": 13.047223091125488,
"max": 13.905513763427734,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2705.27880859375,
"min": 2535.58544921875,
"max": 2829.4677734375,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07047517671034097,
"min": 0.05911132975483732,
"max": 0.07519401556683257,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28190070684136387,
"min": 0.2364453190193493,
"max": 0.3726317275608844,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15974355364839235,
"min": 0.15134727390957814,
"max": 0.20510832848502142,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6389742145935694,
"min": 0.6181908014650438,
"max": 0.9627516944618786,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.5380991539999983e-06,
"min": 2.5380991539999983e-06,
"max": 0.000197238034254,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0152396615999993e-05,
"min": 1.0152396615999993e-05,
"max": 0.00096144017952,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.100846,
"min": 0.100846,
"max": 0.165746,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.403384,
"min": 0.403384,
"max": 0.82048,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 5.2215399999999974e-05,
"min": 5.2215399999999974e-05,
"max": 0.0032907254000000006,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002088615999999999,
"min": 0.0002088615999999999,
"max": 0.016041952000000005,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.045454545454547,
"min": 25.363636363636363,
"max": 27.65909090909091,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1190.0,
"min": 1116.0,
"max": 1493.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.045454545454547,
"min": 25.363636363636363,
"max": 27.65909090909091,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1190.0,
"min": 1116.0,
"max": 1493.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1744014826",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744015705"
},
"total": 878.6037278650001,
"count": 1,
"self": 0.43774447400005556,
"children": {
"run_training.setup": {
"total": 0.023251321999850916,
"count": 1,
"self": 0.023251321999850916
},
"TrainerController.start_learning": {
"total": 878.1427320690002,
"count": 1,
"self": 0.7396353000456202,
"children": {
"TrainerController._reset_env": {
"total": 2.002484493999873,
"count": 1,
"self": 2.002484493999873
},
"TrainerController.advance": {
"total": 875.307620128955,
"count": 36392,
"self": 0.7546325989544584,
"children": {
"env_step": {
"total": 624.4844617490025,
"count": 36392,
"self": 475.44420636804557,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.59203284697924,
"count": 36392,
"self": 2.610926098949676,
"children": {
"TorchPolicy.evaluate": {
"total": 145.98110674802956,
"count": 36392,
"self": 145.98110674802956
}
}
},
"workers": {
"total": 0.4482225339777415,
"count": 36392,
"self": 0.0,
"children": {
"worker_root": {
"total": 875.3422665909873,
"count": 36392,
"is_parallel": true,
"self": 458.74792514104206,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022797660001288023,
"count": 1,
"is_parallel": true,
"self": 0.0007739850002508319,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015057809998779703,
"count": 10,
"is_parallel": true,
"self": 0.0015057809998779703
}
}
},
"UnityEnvironment.step": {
"total": 0.03830807800000002,
"count": 1,
"is_parallel": true,
"self": 0.0006039380000402161,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004521050000221294,
"count": 1,
"is_parallel": true,
"self": 0.0004521050000221294
},
"communicator.exchange": {
"total": 0.03497384999991482,
"count": 1,
"is_parallel": true,
"self": 0.03497384999991482
},
"steps_from_proto": {
"total": 0.0022781850000228587,
"count": 1,
"is_parallel": true,
"self": 0.00043533600023693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018428489997859288,
"count": 10,
"is_parallel": true,
"self": 0.0018428489997859288
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 416.5943414499452,
"count": 36391,
"is_parallel": true,
"self": 19.72895361689416,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.066761758010443,
"count": 36391,
"is_parallel": true,
"self": 11.066761758010443
},
"communicator.exchange": {
"total": 319.7813514570007,
"count": 36391,
"is_parallel": true,
"self": 319.7813514570007
},
"steps_from_proto": {
"total": 66.01727461803989,
"count": 36391,
"is_parallel": true,
"self": 11.884214868036224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.13305975000367,
"count": 363910,
"is_parallel": true,
"self": 54.13305975000367
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 250.06852578099802,
"count": 36392,
"self": 0.9112952680043236,
"children": {
"process_trajectory": {
"total": 55.24219562699318,
"count": 36392,
"self": 54.37556592799251,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8666296990006686,
"count": 8,
"self": 0.8666296990006686
}
}
},
"_update_policy": {
"total": 193.9150348860005,
"count": 181,
"self": 76.92663030999051,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.98840457601,
"count": 9228,
"self": 116.98840457601
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.619998309062794e-07,
"count": 1,
"self": 9.619998309062794e-07
},
"TrainerController._save_models": {
"total": 0.09299118399985673,
"count": 1,
"self": 0.0012585089998538024,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09173267500000293,
"count": 1,
"self": 0.09173267500000293
}
}
}
}
}
}
}