Mattttthew
Revert "First Commit
a8179d5
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.105883002281189,
"min": 1.105883002281189,
"max": 2.716183662414551,
"count": 18
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11240.1953125,
"min": 10538.083984375,
"max": 27756.6796875,
"count": 18
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 29944.0,
"max": 199984.0,
"count": 18
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 29944.0,
"max": 199984.0,
"count": 18
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.162577629089355,
"min": 2.2049355506896973,
"max": 12.162577629089355,
"count": 18
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2371.70263671875,
"min": 414.5278625488281,
"max": 2435.4482421875,
"count": 18
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 18
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 18
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06800207299780667,
"min": 0.0611992703961019,
"max": 0.07773452160094452,
"count": 18
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27200829199122667,
"min": 0.2447970815844076,
"max": 0.36503104102174644,
"count": 18
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21178227407382982,
"min": 0.1825469789990023,
"max": 0.2685693842523238,
"count": 18
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8471290962953193,
"min": 0.7301879159960092,
"max": 1.342846921261619,
"count": 18
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.218097594000008e-06,
"min": 7.218097594000008e-06,
"max": 0.000261318012894,
"count": 18
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.8872390376000034e-05,
"min": 2.8872390376000034e-05,
"max": 0.00116634011122,
"count": 18
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10240600000000001,
"min": 0.10240600000000001,
"max": 0.18710600000000002,
"count": 18
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40962400000000004,
"min": 0.40962400000000004,
"max": 0.8887800000000001,
"count": 18
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00013005940000000016,
"min": 0.00013005940000000016,
"max": 0.004356589400000001,
"count": 18
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005202376000000006,
"min": 0.0005202376000000006,
"max": 0.019450122000000004,
"count": 18
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.795454545454547,
"min": 7.181818181818182,
"max": 24.2,
"count": 18
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1047.0,
"min": 316.0,
"max": 1331.0,
"count": 18
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.795454545454547,
"min": 7.181818181818182,
"max": 24.2,
"count": 18
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1047.0,
"min": 316.0,
"max": 1331.0,
"count": 18
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 18
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 18
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1706630553",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706630968"
},
"total": 414.82036685599996,
"count": 1,
"self": 0.7497639149999031,
"children": {
"run_training.setup": {
"total": 0.049466702000017904,
"count": 1,
"self": 0.049466702000017904
},
"TrainerController.start_learning": {
"total": 414.02113623900004,
"count": 1,
"self": 0.558341403006807,
"children": {
"TrainerController._reset_env": {
"total": 1.8853668110000399,
"count": 1,
"self": 1.8853668110000399
},
"TrainerController.advance": {
"total": 411.4684767389931,
"count": 16394,
"self": 0.25432543296210497,
"children": {
"env_step": {
"total": 411.214151306031,
"count": 16394,
"self": 266.1830963869934,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.76404969201985,
"count": 16394,
"self": 1.3664211610500843,
"children": {
"TorchPolicy.evaluate": {
"total": 143.39762853096977,
"count": 16394,
"self": 143.39762853096977
}
}
},
"workers": {
"total": 0.2670052270177621,
"count": 16394,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.79179329900376,
"count": 16394,
"is_parallel": true,
"self": 204.65875484999265,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002037377999840828,
"count": 1,
"is_parallel": true,
"self": 0.0005944079998698726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014429699999709555,
"count": 10,
"is_parallel": true,
"self": 0.0014429699999709555
}
}
},
"UnityEnvironment.step": {
"total": 0.040581607000149233,
"count": 1,
"is_parallel": true,
"self": 0.0006585530002212181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004449079999631067,
"count": 1,
"is_parallel": true,
"self": 0.0004449079999631067
},
"communicator.exchange": {
"total": 0.0373644690000674,
"count": 1,
"is_parallel": true,
"self": 0.0373644690000674
},
"steps_from_proto": {
"total": 0.002113676999897507,
"count": 1,
"is_parallel": true,
"self": 0.00039274400023714406,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017209329996603628,
"count": 10,
"is_parallel": true,
"self": 0.0017209329996603628
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.1330384490111,
"count": 16393,
"is_parallel": true,
"self": 9.766552981980794,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.097084261992904,
"count": 16393,
"is_parallel": true,
"self": 5.097084261992904
},
"communicator.exchange": {
"total": 161.0735922160152,
"count": 16393,
"is_parallel": true,
"self": 161.0735922160152
},
"steps_from_proto": {
"total": 32.195808989022225,
"count": 16393,
"is_parallel": true,
"self": 6.060813794058959,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.134995194963267,
"count": 163930,
"is_parallel": true,
"self": 26.134995194963267
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0005727390000629384,
"count": 1,
"self": 0.0005727390000629384,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 406.0832429920108,
"count": 634922,
"is_parallel": true,
"self": 13.67291909191249,
"children": {
"process_trajectory": {
"total": 225.95308515109855,
"count": 634922,
"is_parallel": true,
"self": 225.2978584440982,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6552267070003381,
"count": 4,
"is_parallel": true,
"self": 0.6552267070003381
}
}
},
"_update_policy": {
"total": 166.45723874899977,
"count": 81,
"is_parallel": true,
"self": 46.79020327600074,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.66703547299903,
"count": 4128,
"is_parallel": true,
"self": 119.66703547299903
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10837854700002936,
"count": 1,
"self": 0.0018069550001200696,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10657159199990929,
"count": 1,
"self": 0.10657159199990929
}
}
}
}
}
}
}