jajostrains's picture
First Push
69a73e5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.837152898311615,
"min": 0.837152898311615,
"max": 2.8675525188446045,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7956.30126953125,
"min": 7956.30126953125,
"max": 29271.9765625,
"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": 13.117446899414062,
"min": 0.4197595715522766,
"max": 13.117446899414062,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2557.902099609375,
"min": 81.43335723876953,
"max": 2666.78076171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06735356599771573,
"min": 0.06283011708554684,
"max": 0.07099350822733387,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26941426399086293,
"min": 0.25393295273191624,
"max": 0.35496754113666934,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20625049971482334,
"min": 0.11512861019297155,
"max": 0.3096318017618329,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8250019988592934,
"min": 0.4605144407718862,
"max": 1.5481590088091646,
"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.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": 25.84090909090909,
"min": 3.25,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 143.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.25,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 143.0,
"max": 1422.0,
"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": "1752753338",
"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=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": "1752753756"
},
"total": 417.4380278560001,
"count": 1,
"self": 0.39036174099999243,
"children": {
"run_training.setup": {
"total": 0.025088329000027443,
"count": 1,
"self": 0.025088329000027443
},
"TrainerController.start_learning": {
"total": 417.02257778600006,
"count": 1,
"self": 0.33598226499782413,
"children": {
"TrainerController._reset_env": {
"total": 3.097799436999935,
"count": 1,
"self": 3.097799436999935
},
"TrainerController.advance": {
"total": 413.5068066960023,
"count": 18192,
"self": 0.3835575839983676,
"children": {
"env_step": {
"total": 296.23805220601366,
"count": 18192,
"self": 228.1817729630077,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.85096111401026,
"count": 18192,
"self": 1.2258180050037026,
"children": {
"TorchPolicy.evaluate": {
"total": 66.62514310900656,
"count": 18192,
"self": 66.62514310900656
}
}
},
"workers": {
"total": 0.20531812899571378,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 415.69191444199816,
"count": 18192,
"is_parallel": true,
"self": 215.38915150198932,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006539805999977943,
"count": 1,
"is_parallel": true,
"self": 0.003979734999916218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025600710000617255,
"count": 10,
"is_parallel": true,
"self": 0.0025600710000617255
}
}
},
"UnityEnvironment.step": {
"total": 0.037092905000008614,
"count": 1,
"is_parallel": true,
"self": 0.0006627060000710117,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004312920000302256,
"count": 1,
"is_parallel": true,
"self": 0.0004312920000302256
},
"communicator.exchange": {
"total": 0.03393788899995798,
"count": 1,
"is_parallel": true,
"self": 0.03393788899995798
},
"steps_from_proto": {
"total": 0.0020610179999493994,
"count": 1,
"is_parallel": true,
"self": 0.0004194449999204153,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001641573000028984,
"count": 10,
"is_parallel": true,
"self": 0.001641573000028984
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.30276294000885,
"count": 18191,
"is_parallel": true,
"self": 9.73039463500686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3527509429952715,
"count": 18191,
"is_parallel": true,
"self": 5.3527509429952715
},
"communicator.exchange": {
"total": 153.7089511790017,
"count": 18191,
"is_parallel": true,
"self": 153.7089511790017
},
"steps_from_proto": {
"total": 31.510666183005014,
"count": 18191,
"is_parallel": true,
"self": 5.611020677983106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.89964550502191,
"count": 181910,
"is_parallel": true,
"self": 25.89964550502191
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.88519690599026,
"count": 18192,
"self": 0.4242069169933984,
"children": {
"process_trajectory": {
"total": 25.47791167999742,
"count": 18192,
"self": 25.03776273699748,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4401489429999401,
"count": 4,
"self": 0.4401489429999401
}
}
},
"_update_policy": {
"total": 90.98307830899944,
"count": 90,
"self": 37.58351405499775,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.39956425400169,
"count": 4587,
"self": 53.39956425400169
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0620000239214278e-06,
"count": 1,
"self": 1.0620000239214278e-06
},
"TrainerController._save_models": {
"total": 0.08198832599998696,
"count": 1,
"self": 0.000832322000064778,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08115600399992218,
"count": 1,
"self": 0.08115600399992218
}
}
}
}
}
}
}