jeebeekay's picture
First Push
7f2d77e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9515231847763062,
"min": 0.9515231847763062,
"max": 2.842681884765625,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9043.2763671875,
"min": 9043.2763671875,
"max": 29018.09765625,
"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": 12.848380088806152,
"min": 0.3431442081928253,
"max": 12.848380088806152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2505.43408203125,
"min": 66.56997680664062,
"max": 2599.9765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06767506439720426,
"min": 0.061183262710213,
"max": 0.07532585360732971,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27070025758881705,
"min": 0.25713159748285724,
"max": 0.36073578394565387,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20697315617957537,
"min": 0.13136881557818247,
"max": 0.27621976715676927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8278926247183015,
"min": 0.5254752623127299,
"max": 1.3810988357838463,
"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": 24.84090909090909,
"min": 3.8636363636363638,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 170.0,
"max": 1417.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.8636363636363638,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 170.0,
"max": 1417.0,
"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": "1778700362",
"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": "1778700871"
},
"total": 508.4827428110002,
"count": 1,
"self": 0.4365015590005896,
"children": {
"run_training.setup": {
"total": 0.03975865300026271,
"count": 1,
"self": 0.03975865300026271
},
"TrainerController.start_learning": {
"total": 508.00648259899936,
"count": 1,
"self": 0.49503490793313176,
"children": {
"TrainerController._reset_env": {
"total": 3.1748767949998182,
"count": 1,
"self": 3.1748767949998182
},
"TrainerController.advance": {
"total": 504.25255541806564,
"count": 18192,
"self": 0.47700102509543285,
"children": {
"env_step": {
"total": 373.4581172070334,
"count": 18192,
"self": 292.58761449100075,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.57056422500136,
"count": 18192,
"self": 1.5289281770092202,
"children": {
"TorchPolicy.evaluate": {
"total": 79.04163604799214,
"count": 18192,
"self": 79.04163604799214
}
}
},
"workers": {
"total": 0.2999384910312983,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 505.99181045208707,
"count": 18192,
"is_parallel": true,
"self": 250.41571664910907,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008521734999703767,
"count": 1,
"is_parallel": true,
"self": 0.0070976710003378685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014240639993658988,
"count": 10,
"is_parallel": true,
"self": 0.0014240639993658988
}
}
},
"UnityEnvironment.step": {
"total": 0.039941212000030646,
"count": 1,
"is_parallel": true,
"self": 0.0006451419994846219,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004173970000920235,
"count": 1,
"is_parallel": true,
"self": 0.0004173970000920235
},
"communicator.exchange": {
"total": 0.036876187000416394,
"count": 1,
"is_parallel": true,
"self": 0.036876187000416394
},
"steps_from_proto": {
"total": 0.0020024860000376066,
"count": 1,
"is_parallel": true,
"self": 0.00039334400071311393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016091419993244926,
"count": 10,
"is_parallel": true,
"self": 0.0016091419993244926
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.576093802978,
"count": 18191,
"is_parallel": true,
"self": 11.277094521195068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.070636697858845,
"count": 18191,
"is_parallel": true,
"self": 6.070636697858845
},
"communicator.exchange": {
"total": 196.7772059269132,
"count": 18191,
"is_parallel": true,
"self": 196.7772059269132
},
"steps_from_proto": {
"total": 41.45115665701087,
"count": 18191,
"is_parallel": true,
"self": 7.398311148069752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.05284550894112,
"count": 181910,
"is_parallel": true,
"self": 34.05284550894112
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 130.3174371859368,
"count": 18192,
"self": 0.6480465619592906,
"children": {
"process_trajectory": {
"total": 28.61985061297719,
"count": 18192,
"self": 28.195213144977515,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4246374679996734,
"count": 4,
"self": 0.4246374679996734
}
}
},
"_update_policy": {
"total": 101.04954001100032,
"count": 90,
"self": 42.75534160198731,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.294198409013006,
"count": 4587,
"self": 58.294198409013006
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0740004654508084e-06,
"count": 1,
"self": 1.0740004654508084e-06
},
"TrainerController._save_models": {
"total": 0.08401440400029969,
"count": 1,
"self": 0.0007390969994958141,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08327530700080388,
"count": 1,
"self": 0.08327530700080388
}
}
}
}
}
}
}