ntn201105's picture
First Push
d0634f0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9286935925483704,
"min": 0.9286935925483704,
"max": 2.8463265895843506,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8826.3037109375,
"min": 8826.3037109375,
"max": 29055.302734375,
"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": 13.250292778015137,
"min": 0.300916463136673,
"max": 13.250292778015137,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2583.80712890625,
"min": 58.37779235839844,
"max": 2698.4443359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06342236061805036,
"min": 0.061674468868124464,
"max": 0.0728194430685036,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25368944247220143,
"min": 0.24669787547249786,
"max": 0.364097215342518,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1934872617324193,
"min": 0.11898786940967992,
"max": 0.2889329462366945,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7739490469296773,
"min": 0.4759514776387197,
"max": 1.330764672627636,
"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": 25.772727272727273,
"min": 3.25,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 143.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.25,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 143.0,
"max": 1419.0,
"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": "1739123625",
"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": "1739124049"
},
"total": 423.13906636599995,
"count": 1,
"self": 0.43953801699990436,
"children": {
"run_training.setup": {
"total": 0.025777093999977296,
"count": 1,
"self": 0.025777093999977296
},
"TrainerController.start_learning": {
"total": 422.67375125500007,
"count": 1,
"self": 0.33792395499847316,
"children": {
"TrainerController._reset_env": {
"total": 2.9989115239999364,
"count": 1,
"self": 2.9989115239999364
},
"TrainerController.advance": {
"total": 419.25101159200176,
"count": 18192,
"self": 0.3382134980074625,
"children": {
"env_step": {
"total": 293.8534109109978,
"count": 18192,
"self": 222.70077164700058,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.95445935200416,
"count": 18192,
"self": 1.2142732220008838,
"children": {
"TorchPolicy.evaluate": {
"total": 69.74018613000328,
"count": 18192,
"self": 69.74018613000328
}
}
},
"workers": {
"total": 0.19817991199306562,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.1989419630071,
"count": 18192,
"is_parallel": true,
"self": 225.67307058000517,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0057353890000513275,
"count": 1,
"is_parallel": true,
"self": 0.004156888000238723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015785009998126043,
"count": 10,
"is_parallel": true,
"self": 0.0015785009998126043
}
}
},
"UnityEnvironment.step": {
"total": 0.0345660109999244,
"count": 1,
"is_parallel": true,
"self": 0.0005288039998276872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037901200005308056,
"count": 1,
"is_parallel": true,
"self": 0.00037901200005308056
},
"communicator.exchange": {
"total": 0.031826473000023725,
"count": 1,
"is_parallel": true,
"self": 0.031826473000023725
},
"steps_from_proto": {
"total": 0.0018317220000199086,
"count": 1,
"is_parallel": true,
"self": 0.00034114999994017126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014905720000797373,
"count": 10,
"is_parallel": true,
"self": 0.0014905720000797373
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.5258713830019,
"count": 18191,
"is_parallel": true,
"self": 9.381264475989042,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.40526751600089,
"count": 18191,
"is_parallel": true,
"self": 5.40526751600089
},
"communicator.exchange": {
"total": 150.69047070201054,
"count": 18191,
"is_parallel": true,
"self": 150.69047070201054
},
"steps_from_proto": {
"total": 30.048868689001438,
"count": 18191,
"is_parallel": true,
"self": 5.239313689979099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.80955499902234,
"count": 181910,
"is_parallel": true,
"self": 24.80955499902234
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.05938718299649,
"count": 18192,
"self": 0.39131506599335353,
"children": {
"process_trajectory": {
"total": 26.894802502003472,
"count": 18192,
"self": 26.354704157003425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5400983450000467,
"count": 4,
"self": 0.5400983450000467
}
}
},
"_update_policy": {
"total": 97.77326961499966,
"count": 90,
"self": 39.952531561995215,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.82073805300445,
"count": 4587,
"self": 57.82073805300445
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.689999049238395e-07,
"count": 1,
"self": 8.689999049238395e-07
},
"TrainerController._save_models": {
"total": 0.08590331499999593,
"count": 1,
"self": 0.0009383710000747669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08496494399992116,
"count": 1,
"self": 0.08496494399992116
}
}
}
}
}
}
}