Darian616's picture
First Push
6280cd9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7930983304977417,
"min": 0.7930983304977417,
"max": 2.8466577529907227,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7537.6064453125,
"min": 7537.6064453125,
"max": 29058.681640625,
"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": 12.772183418273926,
"min": 0.4488796293735504,
"max": 12.901885032653809,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2490.57568359375,
"min": 87.08264923095703,
"max": 2644.886474609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07137200325629309,
"min": 0.06294861984739221,
"max": 0.0777665330410944,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28548801302517235,
"min": 0.26048803224237455,
"max": 0.3611521075580123,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18563832349929155,
"min": 0.13904857306795962,
"max": 0.2784439245275423,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7425532939971662,
"min": 0.5561942922718385,
"max": 1.3922196226377115,
"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": 24.90909090909091,
"min": 4.25,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1096.0,
"min": 187.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.90909090909091,
"min": 4.25,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1096.0,
"min": 187.0,
"max": 1406.0,
"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": "1741338900",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741339333"
},
"total": 433.5663319329999,
"count": 1,
"self": 0.43737537699985296,
"children": {
"run_training.setup": {
"total": 0.03907976499999677,
"count": 1,
"self": 0.03907976499999677
},
"TrainerController.start_learning": {
"total": 433.08987679100005,
"count": 1,
"self": 0.3545142509932475,
"children": {
"TrainerController._reset_env": {
"total": 3.5253828660000863,
"count": 1,
"self": 3.5253828660000863
},
"TrainerController.advance": {
"total": 429.12279241400665,
"count": 18192,
"self": 0.3735217209990651,
"children": {
"env_step": {
"total": 304.97585144100526,
"count": 18192,
"self": 232.81683588000544,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.95340034900539,
"count": 18192,
"self": 1.293635455003141,
"children": {
"TorchPolicy.evaluate": {
"total": 70.65976489400225,
"count": 18192,
"self": 70.65976489400225
}
}
},
"workers": {
"total": 0.20561521199442723,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 431.6529431980034,
"count": 18192,
"is_parallel": true,
"self": 227.57211211200718,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.015264339999930598,
"count": 1,
"is_parallel": true,
"self": 0.01374809199990068,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015162480000299183,
"count": 10,
"is_parallel": true,
"self": 0.0015162480000299183
}
}
},
"UnityEnvironment.step": {
"total": 0.04024585100000877,
"count": 1,
"is_parallel": true,
"self": 0.000719079000077727,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040398900000582216,
"count": 1,
"is_parallel": true,
"self": 0.00040398900000582216
},
"communicator.exchange": {
"total": 0.036786796999990656,
"count": 1,
"is_parallel": true,
"self": 0.036786796999990656
},
"steps_from_proto": {
"total": 0.0023359859999345645,
"count": 1,
"is_parallel": true,
"self": 0.0004416210000499632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018943649998846013,
"count": 10,
"is_parallel": true,
"self": 0.0018943649998846013
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.08083108599624,
"count": 18191,
"is_parallel": true,
"self": 9.71966983198547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.467718884012811,
"count": 18191,
"is_parallel": true,
"self": 5.467718884012811
},
"communicator.exchange": {
"total": 156.7491874780054,
"count": 18191,
"is_parallel": true,
"self": 156.7491874780054
},
"steps_from_proto": {
"total": 32.144254891992546,
"count": 18191,
"is_parallel": true,
"self": 5.734710466013098,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.409544425979448,
"count": 181910,
"is_parallel": true,
"self": 26.409544425979448
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.77341925200233,
"count": 18192,
"self": 0.44594884299874593,
"children": {
"process_trajectory": {
"total": 27.38219714200386,
"count": 18192,
"self": 26.854732364003894,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5274647779999668,
"count": 4,
"self": 0.5274647779999668
}
}
},
"_update_policy": {
"total": 95.94527326699972,
"count": 90,
"self": 38.84147420199838,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.10379906500134,
"count": 4587,
"self": 57.10379906500134
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.230000503317569e-07,
"count": 1,
"self": 8.230000503317569e-07
},
"TrainerController._save_models": {
"total": 0.08718643700001394,
"count": 1,
"self": 0.0008898749999843858,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08629656200002955,
"count": 1,
"self": 0.08629656200002955
}
}
}
}
}
}
}