Protao's picture
First Push
6e8effe
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0345569849014282,
"min": 1.02930748462677,
"max": 2.8764896392822266,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9912.0908203125,
"min": 9912.0908203125,
"max": 29458.130859375,
"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": 12.754023551940918,
"min": 0.3729410469532013,
"max": 12.754023551940918,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2487.03466796875,
"min": 72.3505630493164,
"max": 2589.74462890625,
"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.Losses.PolicyLoss.mean": {
"value": 0.07099424521370298,
"min": 0.05632360612199751,
"max": 0.07823664570751135,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28397698085481193,
"min": 0.22529442448799003,
"max": 0.3911832285375567,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19760590484913657,
"min": 0.10007866072541505,
"max": 0.27961669526263777,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7904236193965463,
"min": 0.4003146429016602,
"max": 1.3193040054802803,
"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.CumulativeReward.mean": {
"value": 24.613636363636363,
"min": 2.8636363636363638,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 126.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 2.8636363636363638,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 126.0,
"max": 1389.0,
"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": "1701833944",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701834411"
},
"total": 467.411066785,
"count": 1,
"self": 0.8707148270002563,
"children": {
"run_training.setup": {
"total": 0.08613686099988627,
"count": 1,
"self": 0.08613686099988627
},
"TrainerController.start_learning": {
"total": 466.45421509699986,
"count": 1,
"self": 0.5832708580076087,
"children": {
"TrainerController._reset_env": {
"total": 3.882958515000155,
"count": 1,
"self": 3.882958515000155
},
"TrainerController.advance": {
"total": 461.86022320699203,
"count": 18215,
"self": 0.2879469410099773,
"children": {
"env_step": {
"total": 461.57227626598205,
"count": 18215,
"self": 312.0943345990054,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.19506727599492,
"count": 18215,
"self": 1.455636787000003,
"children": {
"TorchPolicy.evaluate": {
"total": 147.7394304889949,
"count": 18215,
"self": 147.7394304889949
}
}
},
"workers": {
"total": 0.28287439098176037,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 465.25247495500776,
"count": 18215,
"is_parallel": true,
"self": 229.22844109800621,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00695975600001475,
"count": 1,
"is_parallel": true,
"self": 0.004821516999754749,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021382390002600005,
"count": 10,
"is_parallel": true,
"self": 0.0021382390002600005
}
}
},
"UnityEnvironment.step": {
"total": 0.037628106000056505,
"count": 1,
"is_parallel": true,
"self": 0.0006387030002770189,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003929049998987466,
"count": 1,
"is_parallel": true,
"self": 0.0003929049998987466
},
"communicator.exchange": {
"total": 0.034547972999916965,
"count": 1,
"is_parallel": true,
"self": 0.034547972999916965
},
"steps_from_proto": {
"total": 0.0020485249999637745,
"count": 1,
"is_parallel": true,
"self": 0.0004028149999157904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001645710000047984,
"count": 10,
"is_parallel": true,
"self": 0.001645710000047984
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.02403385700154,
"count": 18214,
"is_parallel": true,
"self": 10.284704255988345,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.19020007602353,
"count": 18214,
"is_parallel": true,
"self": 5.19020007602353
},
"communicator.exchange": {
"total": 187.4855332579973,
"count": 18214,
"is_parallel": true,
"self": 187.4855332579973
},
"steps_from_proto": {
"total": 33.06359626699236,
"count": 18214,
"is_parallel": true,
"self": 6.189304543964909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.874291723027454,
"count": 182140,
"is_parallel": true,
"self": 26.874291723027454
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000150100999917413,
"count": 1,
"self": 0.000150100999917413,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.0296400870204,
"count": 482231,
"is_parallel": true,
"self": 10.135300961045232,
"children": {
"process_trajectory": {
"total": 259.50341344797584,
"count": 482231,
"is_parallel": true,
"self": 258.38288658297597,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1205268649998743,
"count": 4,
"is_parallel": true,
"self": 1.1205268649998743
}
}
},
"_update_policy": {
"total": 188.39092567799935,
"count": 90,
"is_parallel": true,
"self": 57.93155747599235,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.459368202007,
"count": 4587,
"is_parallel": true,
"self": 130.459368202007
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12761241600014728,
"count": 1,
"self": 0.0011057540002639143,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12650666199988336,
"count": 1,
"self": 0.12650666199988336
}
}
}
}
}
}
}