Boxnixta's picture
First Push
a51b19d verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9359989762306213,
"min": 0.9359989762306213,
"max": 2.8769099712371826,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8895.734375,
"min": 8895.734375,
"max": 29367.49609375,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249944.0,
"min": 9952.0,
"max": 249944.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.133615493774414,
"min": 0.11970428377389908,
"max": 13.133615493774414,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2547.92138671875,
"min": 23.222631454467773,
"max": 2663.593017578125,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.25,
"min": 3.0681818181818183,
"max": 26.25,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1155.0,
"min": 135.0,
"max": 1440.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.25,
"min": 3.0681818181818183,
"max": 26.25,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1155.0,
"min": 135.0,
"max": 1440.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.052930760893785324,
"min": 0.041167680390612485,
"max": 0.060937015371867645,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.15879228268135598,
"min": 0.08233536078122497,
"max": 0.16516317418584853,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19463962077818533,
"min": 0.10332053743509784,
"max": 0.3163214908498857,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.583918862334556,
"min": 0.20664107487019567,
"max": 0.9489644725496571,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.0272982432000126e-06,
"min": 7.0272982432000126e-06,
"max": 0.0003912704021824,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.1081894729600038e-05,
"min": 2.1081894729600038e-05,
"max": 0.0011298816175296003,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10175680000000002,
"min": 0.10175680000000002,
"max": 0.19781760000000004,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.30527040000000005,
"min": 0.21963520000000003,
"max": 0.5824704,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.766432000000014e-05,
"min": 9.766432000000014e-05,
"max": 0.004891098240000001,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002929929600000004,
"min": 0.0002929929600000004,
"max": 0.01412527296,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1781936674",
"python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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=SnowballTarget2 --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": "1781937249"
},
"total": 574.758155145,
"count": 1,
"self": 0.4831699740000204,
"children": {
"run_training.setup": {
"total": 0.036426703000017824,
"count": 1,
"self": 0.036426703000017824
},
"TrainerController.start_learning": {
"total": 574.2385584680001,
"count": 1,
"self": 0.5108760719940619,
"children": {
"TrainerController._reset_env": {
"total": 3.278190570999982,
"count": 1,
"self": 3.278190570999982
},
"TrainerController.advance": {
"total": 570.3670110620061,
"count": 22728,
"self": 0.5123257180132441,
"children": {
"env_step": {
"total": 443.1102792280019,
"count": 22728,
"self": 346.2221604409905,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.58980176199861,
"count": 22728,
"self": 1.7276849489958863,
"children": {
"TorchPolicy.evaluate": {
"total": 94.86211681300273,
"count": 22728,
"self": 94.86211681300273
}
}
},
"workers": {
"total": 0.2983170250128069,
"count": 22728,
"self": 0.0,
"children": {
"worker_root": {
"total": 572.1520919579938,
"count": 22728,
"is_parallel": true,
"self": 267.82451410701253,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005472177000001466,
"count": 1,
"is_parallel": true,
"self": 0.003380646000039178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020915309999622878,
"count": 10,
"is_parallel": true,
"self": 0.0020915309999622878
}
}
},
"UnityEnvironment.step": {
"total": 0.04186392099995828,
"count": 1,
"is_parallel": true,
"self": 0.0006247979999898234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004850980000128402,
"count": 1,
"is_parallel": true,
"self": 0.0004850980000128402
},
"communicator.exchange": {
"total": 0.03849745799999482,
"count": 1,
"is_parallel": true,
"self": 0.03849745799999482
},
"steps_from_proto": {
"total": 0.0022565669999607962,
"count": 1,
"is_parallel": true,
"self": 0.00045256199990717505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018040050000536212,
"count": 10,
"is_parallel": true,
"self": 0.0018040050000536212
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 304.32757785098124,
"count": 22727,
"is_parallel": true,
"self": 13.975937304995455,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.560412337992204,
"count": 22727,
"is_parallel": true,
"self": 7.560412337992204
},
"communicator.exchange": {
"total": 231.96577029800045,
"count": 22727,
"is_parallel": true,
"self": 231.96577029800045
},
"steps_from_proto": {
"total": 50.82545790999313,
"count": 22727,
"is_parallel": true,
"self": 8.682821108958535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 42.1426368010346,
"count": 227270,
"is_parallel": true,
"self": 42.1426368010346
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.74440611599096,
"count": 22728,
"self": 0.5878770179891717,
"children": {
"process_trajectory": {
"total": 32.12302175400197,
"count": 22728,
"self": 31.57767556300206,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5453461909999078,
"count": 5,
"self": 0.5453461909999078
}
}
},
"_update_policy": {
"total": 94.03350734399982,
"count": 68,
"self": 50.20795517299854,
"children": {
"TorchPPOOptimizer.update": {
"total": 43.82555217100128,
"count": 3195,
"self": 43.82555217100128
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1199999789823778e-06,
"count": 1,
"self": 1.1199999789823778e-06
},
"TrainerController._save_models": {
"total": 0.08247964299994237,
"count": 1,
"self": 0.0007680149999487185,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08171162799999365,
"count": 1,
"self": 0.08171162799999365
}
}
}
}
}
}
}