jmartin233's picture
First Push
b97c5e0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7640905976295471,
"min": 0.7640905976295471,
"max": 2.8514814376831055,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7261.9169921875,
"min": 7261.9169921875,
"max": 29107.921875,
"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": 13.106101989746094,
"min": 0.5654761791229248,
"max": 13.106101989746094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2555.68994140625,
"min": 109.70237731933594,
"max": 2678.74658203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06466607587878803,
"min": 0.06273893102757831,
"max": 0.07878241741712497,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2586643035151521,
"min": 0.25095572411031325,
"max": 0.36996841204567243,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18567248806357384,
"min": 0.12043919632503508,
"max": 0.3295916215461843,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7426899522542953,
"min": 0.4817567853001403,
"max": 1.6479581077309216,
"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": 25.931818181818183,
"min": 3.7954545454545454,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 167.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.7954545454545454,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 167.0,
"max": 1426.0,
"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": "1755459802",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1755460241"
},
"total": 439.767270499,
"count": 1,
"self": 0.43459496600007697,
"children": {
"run_training.setup": {
"total": 0.03555021099998612,
"count": 1,
"self": 0.03555021099998612
},
"TrainerController.start_learning": {
"total": 439.29712532199994,
"count": 1,
"self": 0.3891322439955047,
"children": {
"TrainerController._reset_env": {
"total": 3.2566823949999844,
"count": 1,
"self": 3.2566823949999844
},
"TrainerController.advance": {
"total": 435.56350089900445,
"count": 18192,
"self": 0.3878773089945753,
"children": {
"env_step": {
"total": 314.7918969740073,
"count": 18192,
"self": 242.9905408740126,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.57634095000253,
"count": 18192,
"self": 1.2799933450123717,
"children": {
"TorchPolicy.evaluate": {
"total": 70.29634760499016,
"count": 18192,
"self": 70.29634760499016
}
}
},
"workers": {
"total": 0.22501514999214578,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.81013710500247,
"count": 18192,
"is_parallel": true,
"self": 224.64423276499292,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00595542700000351,
"count": 1,
"is_parallel": true,
"self": 0.0043070489999763595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016483780000271508,
"count": 10,
"is_parallel": true,
"self": 0.0016483780000271508
}
}
},
"UnityEnvironment.step": {
"total": 0.03530056599993259,
"count": 1,
"is_parallel": true,
"self": 0.0005979749997777617,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003992260000131864,
"count": 1,
"is_parallel": true,
"self": 0.0003992260000131864
},
"communicator.exchange": {
"total": 0.032290441000100145,
"count": 1,
"is_parallel": true,
"self": 0.032290441000100145
},
"steps_from_proto": {
"total": 0.002012924000041494,
"count": 1,
"is_parallel": true,
"self": 0.0004487509997943562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015641730002471377,
"count": 10,
"is_parallel": true,
"self": 0.0015641730002471377
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.16590434000955,
"count": 18191,
"is_parallel": true,
"self": 10.121999268016907,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.828645101003076,
"count": 18191,
"is_parallel": true,
"self": 5.828645101003076
},
"communicator.exchange": {
"total": 163.94678236799268,
"count": 18191,
"is_parallel": true,
"self": 163.94678236799268
},
"steps_from_proto": {
"total": 33.26847760299688,
"count": 18191,
"is_parallel": true,
"self": 5.899245682002629,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.369231920994253,
"count": 181910,
"is_parallel": true,
"self": 27.369231920994253
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.3837266160026,
"count": 18192,
"self": 0.4598219090185012,
"children": {
"process_trajectory": {
"total": 26.99306028898411,
"count": 18192,
"self": 26.563670601984086,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42938968700002533,
"count": 4,
"self": 0.42938968700002533
}
}
},
"_update_policy": {
"total": 92.93084441799999,
"count": 90,
"self": 38.53308993300334,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.39775448499665,
"count": 4587,
"self": 54.39775448499665
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.049999789567664e-07,
"count": 1,
"self": 9.049999789567664e-07
},
"TrainerController._save_models": {
"total": 0.08780887900002199,
"count": 1,
"self": 0.0009229549998508446,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08688592400017114,
"count": 1,
"self": 0.08688592400017114
}
}
}
}
}
}
}