Synthcite24's picture
First Push
56bb9c1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.708411455154419,
"min": 0.708411455154419,
"max": 2.838571310043335,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6732.7421875,
"min": 6732.7421875,
"max": 28976.13671875,
"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": 12.567303657531738,
"min": 0.21838878095149994,
"max": 12.567303657531738,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2450.624267578125,
"min": 42.36742401123047,
"max": 2516.25927734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06962058262003407,
"min": 0.06356548715177948,
"max": 0.07857827675716002,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27848233048013626,
"min": 0.2612107958605823,
"max": 0.3880387255039215,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19716472653489486,
"min": 0.10677806370407708,
"max": 0.27001102020343143,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7886589061395795,
"min": 0.4271122548163083,
"max": 1.3295015391765856,
"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": 25.136363636363637,
"min": 2.9545454545454546,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 130.0,
"max": 1356.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 2.9545454545454546,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 130.0,
"max": 1356.0,
"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": "1740449416",
"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": "1740449892"
},
"total": 475.51981489900004,
"count": 1,
"self": 0.48423815600006037,
"children": {
"run_training.setup": {
"total": 0.03420006999999714,
"count": 1,
"self": 0.03420006999999714
},
"TrainerController.start_learning": {
"total": 475.001376673,
"count": 1,
"self": 0.37913597298188506,
"children": {
"TrainerController._reset_env": {
"total": 3.6325262149999844,
"count": 1,
"self": 3.6325262149999844
},
"TrainerController.advance": {
"total": 470.8757173410179,
"count": 18192,
"self": 0.41292841600159136,
"children": {
"env_step": {
"total": 336.9525224830072,
"count": 18192,
"self": 255.5650504420205,
"children": {
"SubprocessEnvManager._take_step": {
"total": 81.15406787600568,
"count": 18192,
"self": 1.4300262689984038,
"children": {
"TorchPolicy.evaluate": {
"total": 79.72404160700728,
"count": 18192,
"self": 79.72404160700728
}
}
},
"workers": {
"total": 0.23340416498103878,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 473.4183000920209,
"count": 18192,
"is_parallel": true,
"self": 248.92335618601692,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007081180999989556,
"count": 1,
"is_parallel": true,
"self": 0.004600267000341773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024809139996477825,
"count": 10,
"is_parallel": true,
"self": 0.0024809139996477825
}
}
},
"UnityEnvironment.step": {
"total": 0.04100787100003345,
"count": 1,
"is_parallel": true,
"self": 0.0006742540000459485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004151570000203719,
"count": 1,
"is_parallel": true,
"self": 0.0004151570000203719
},
"communicator.exchange": {
"total": 0.03779851399997369,
"count": 1,
"is_parallel": true,
"self": 0.03779851399997369
},
"steps_from_proto": {
"total": 0.0021199459999934334,
"count": 1,
"is_parallel": true,
"self": 0.0004262879997440905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016936580002493429,
"count": 10,
"is_parallel": true,
"self": 0.0016936580002493429
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.49494390600398,
"count": 18191,
"is_parallel": true,
"self": 10.619066116016484,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.149074385003473,
"count": 18191,
"is_parallel": true,
"self": 6.149074385003473
},
"communicator.exchange": {
"total": 171.8146626939922,
"count": 18191,
"is_parallel": true,
"self": 171.8146626939922
},
"steps_from_proto": {
"total": 35.91214071099182,
"count": 18191,
"is_parallel": true,
"self": 6.353090946975044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.559049764016777,
"count": 181910,
"is_parallel": true,
"self": 29.559049764016777
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 133.51026644200908,
"count": 18192,
"self": 0.45532363200220516,
"children": {
"process_trajectory": {
"total": 29.77375243800668,
"count": 18192,
"self": 29.20219943800646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5715530000002218,
"count": 4,
"self": 0.5715530000002218
}
}
},
"_update_policy": {
"total": 103.2811903720002,
"count": 90,
"self": 42.00069316499025,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.280497207009944,
"count": 4587,
"self": 61.280497207009944
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2230000265844865e-06,
"count": 1,
"self": 1.2230000265844865e-06
},
"TrainerController._save_models": {
"total": 0.11399592100019618,
"count": 1,
"self": 0.0013598210000509425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11263610000014523,
"count": 1,
"self": 0.11263610000014523
}
}
}
}
}
}
}