loke-07's picture
First Push
40a9076 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.88221675157547,
"min": 0.88221675157547,
"max": 2.8539600372314453,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8384.587890625,
"min": 8384.587890625,
"max": 29133.224609375,
"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": 2.6502153873443604,
"min": 0.20125359296798706,
"max": 2.661203622817993,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 516.7919921875,
"min": 39.04319763183594,
"max": 545.5467529296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.044099122092029576,
"min": 0.04344330653293582,
"max": 0.05162589690327877,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1763964883681183,
"min": 0.17377322613174329,
"max": 0.25812948451639384,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.14809211404062808,
"min": 0.06815778824966401,
"max": 0.16252048490568996,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5923684561625123,
"min": 0.27263115299865603,
"max": 0.7853336783125997,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.00029188200270599996,
"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": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"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": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.181818181818183,
"min": 3.4545454545454546,
"max": 26.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1152.0,
"min": 152.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.181818181818183,
"min": 3.4545454545454546,
"max": 26.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1152.0,
"min": 152.0,
"max": 1423.0,
"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": "1752778708",
"python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752779133"
},
"total": 425.93662765499994,
"count": 1,
"self": 0.4525254989998757,
"children": {
"run_training.setup": {
"total": 0.024307805000034932,
"count": 1,
"self": 0.024307805000034932
},
"TrainerController.start_learning": {
"total": 425.459794351,
"count": 1,
"self": 0.31178381302424896,
"children": {
"TrainerController._reset_env": {
"total": 3.6721756930000993,
"count": 1,
"self": 3.6721756930000993
},
"TrainerController.advance": {
"total": 421.38121475097546,
"count": 18192,
"self": 0.33956804496597215,
"children": {
"env_step": {
"total": 285.50193998000213,
"count": 18192,
"self": 218.87045856200007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.43102013300722,
"count": 18192,
"self": 1.2034541370071565,
"children": {
"TorchPolicy.evaluate": {
"total": 65.22756599600007,
"count": 18192,
"self": 65.22756599600007
}
}
},
"workers": {
"total": 0.2004612849948444,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.0921291620118,
"count": 18192,
"is_parallel": true,
"self": 232.22442876000127,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00510643000006894,
"count": 1,
"is_parallel": true,
"self": 0.0036560320004355162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014503979996334238,
"count": 10,
"is_parallel": true,
"self": 0.0014503979996334238
}
}
},
"UnityEnvironment.step": {
"total": 0.03397533699990163,
"count": 1,
"is_parallel": true,
"self": 0.0005950989998382283,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039066300018930633,
"count": 1,
"is_parallel": true,
"self": 0.00039066300018930633
},
"communicator.exchange": {
"total": 0.031168452999963847,
"count": 1,
"is_parallel": true,
"self": 0.031168452999963847
},
"steps_from_proto": {
"total": 0.0018211219999102468,
"count": 1,
"is_parallel": true,
"self": 0.0003554410002379882,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014656809996722586,
"count": 10,
"is_parallel": true,
"self": 0.0014656809996722586
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 191.86770040201054,
"count": 18191,
"is_parallel": true,
"self": 9.652435906029268,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.07214130799548,
"count": 18191,
"is_parallel": true,
"self": 5.07214130799548
},
"communicator.exchange": {
"total": 147.12952468198978,
"count": 18191,
"is_parallel": true,
"self": 147.12952468198978
},
"steps_from_proto": {
"total": 30.013598505996015,
"count": 18191,
"is_parallel": true,
"self": 5.344533042021794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.66906546397422,
"count": 181910,
"is_parallel": true,
"self": 24.66906546397422
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 135.53970672600735,
"count": 18192,
"self": 0.37451298598989524,
"children": {
"process_trajectory": {
"total": 26.76802038801702,
"count": 18192,
"self": 26.250815853017002,
"children": {
"RLTrainer._checkpoint": {
"total": 0.517204535000019,
"count": 4,
"self": 0.517204535000019
}
}
},
"_update_policy": {
"total": 108.39717335200044,
"count": 90,
"self": 60.53472416899831,
"children": {
"TorchPPOOptimizer.update": {
"total": 47.86244918300213,
"count": 3600,
"self": 47.86244918300213
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.480001270072535e-07,
"count": 1,
"self": 8.480001270072535e-07
},
"TrainerController._save_models": {
"total": 0.09461924600009297,
"count": 1,
"self": 0.001278145000242148,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09334110099985082,
"count": 1,
"self": 0.09334110099985082
}
}
}
}
}
}
}