mikedata's picture
SnowballTarget ppo first push
0fad5ee verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8813005685806274,
"min": 0.8813005685806274,
"max": 2.809023857116699,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8375.880859375,
"min": 8375.880859375,
"max": 28674.515625,
"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": 13.33371639251709,
"min": 0.4574029743671417,
"max": 13.33371639251709,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2600.07470703125,
"min": 88.73617553710938,
"max": 2686.40869140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07408617717004584,
"min": 0.06303475818186759,
"max": 0.07448137697540326,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29634470868018337,
"min": 0.25213903272747035,
"max": 0.35849986666991535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20160899569883067,
"min": 0.16028823259368757,
"max": 0.2685976509223966,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8064359827953227,
"min": 0.6411529303747503,
"max": 1.3143814425258076,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.694009730600002e-05,
"min": 2.694009730600002e-05,
"max": 0.000972940002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00010776038922400007,
"min": 0.00010776038922400007,
"max": 0.00461720003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 1.2424600000000003e-05,
"min": 1.2424600000000003e-05,
"max": 9.75646e-05,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.969840000000001e-05,
"min": 4.969840000000001e-05,
"max": 0.0004655480000000001,
"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": 26.068181818181817,
"min": 4.636363636363637,
"max": 26.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 204.0,
"max": 1444.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 4.636363636363637,
"max": 26.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 204.0,
"max": 1444.0,
"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": "1746452371",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746452867"
},
"total": 495.6087944029998,
"count": 1,
"self": 0.42725330099983694,
"children": {
"run_training.setup": {
"total": 0.02101102799997534,
"count": 1,
"self": 0.02101102799997534
},
"TrainerController.start_learning": {
"total": 495.160530074,
"count": 1,
"self": 0.3669364770153152,
"children": {
"TrainerController._reset_env": {
"total": 2.024544578999894,
"count": 1,
"self": 2.024544578999894
},
"TrainerController.advance": {
"total": 492.6426633179849,
"count": 18192,
"self": 0.3865551020367093,
"children": {
"env_step": {
"total": 304.3983874479436,
"count": 18192,
"self": 232.5340523769587,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.64313413599689,
"count": 18192,
"self": 1.2821910749444214,
"children": {
"TorchPolicy.evaluate": {
"total": 70.36094306105247,
"count": 18192,
"self": 70.36094306105247
}
}
},
"workers": {
"total": 0.22120093498801907,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.5357914080282,
"count": 18192,
"is_parallel": true,
"self": 289.8674726450424,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020110179998482636,
"count": 1,
"is_parallel": true,
"self": 0.00061654199998884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013944759998594236,
"count": 10,
"is_parallel": true,
"self": 0.0013944759998594236
}
}
},
"UnityEnvironment.step": {
"total": 0.03493291500012674,
"count": 1,
"is_parallel": true,
"self": 0.0005755000001954613,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038601899996137945,
"count": 1,
"is_parallel": true,
"self": 0.00038601899996137945
},
"communicator.exchange": {
"total": 0.032210818000066865,
"count": 1,
"is_parallel": true,
"self": 0.032210818000066865
},
"steps_from_proto": {
"total": 0.0017605779999030347,
"count": 1,
"is_parallel": true,
"self": 0.00034319999986109906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014173780000419356,
"count": 10,
"is_parallel": true,
"self": 0.0014173780000419356
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.6683187629858,
"count": 18191,
"is_parallel": true,
"self": 9.702216202011186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.493287405003684,
"count": 18191,
"is_parallel": true,
"self": 5.493287405003684
},
"communicator.exchange": {
"total": 156.6354321809822,
"count": 18191,
"is_parallel": true,
"self": 156.6354321809822
},
"steps_from_proto": {
"total": 31.837382974988714,
"count": 18191,
"is_parallel": true,
"self": 5.827859182032398,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.009523792956315,
"count": 181910,
"is_parallel": true,
"self": 26.009523792956315
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 187.85772076800458,
"count": 18192,
"self": 0.4807199240085538,
"children": {
"process_trajectory": {
"total": 28.022371117996045,
"count": 18192,
"self": 27.493580777996158,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5287903399998868,
"count": 4,
"self": 0.5287903399998868
}
}
},
"_update_policy": {
"total": 159.35462972599998,
"count": 90,
"self": 64.46185679400742,
"children": {
"TorchPPOOptimizer.update": {
"total": 94.89277293199257,
"count": 7645,
"self": 94.89277293199257
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.099999260797631e-07,
"count": 1,
"self": 9.099999260797631e-07
},
"TrainerController._save_models": {
"total": 0.1263847899999746,
"count": 1,
"self": 0.001550761000089551,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12483402899988505,
"count": 1,
"self": 0.12483402899988505
}
}
}
}
}
}
}