cparedes's picture
Entrenamiento final SnowballTarget con CPU
1c0ecfe verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0205459594726562,
"min": 1.0205459594726562,
"max": 2.8709664344787598,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9744.1728515625,
"min": 9744.1728515625,
"max": 29433.1484375,
"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": 12.755438804626465,
"min": 0.32058465480804443,
"max": 12.755438804626465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2487.310546875,
"min": 62.193424224853516,
"max": 2601.20068359375,
"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.Losses.PolicyLoss.mean": {
"value": 0.06385184221218486,
"min": 0.0607186437717995,
"max": 0.07636889245294894,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25540736884873944,
"min": 0.242874575087198,
"max": 0.38184446226474467,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19837095719926498,
"min": 0.12278029439039528,
"max": 0.2784132146952199,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7934838287970599,
"min": 0.49112117756158113,
"max": 1.3920660734760995,
"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.CumulativeReward.mean": {
"value": 24.954545454545453,
"min": 3.340909090909091,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 147.0,
"max": 1370.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.340909090909091,
"max": 25.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 147.0,
"max": 1370.0,
"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": "1744413376",
"python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]",
"command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetCPU --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": "1744413955"
},
"total": 579.088548037,
"count": 1,
"self": 0.5398945050000066,
"children": {
"run_training.setup": {
"total": 0.031620893999956934,
"count": 1,
"self": 0.031620893999956934
},
"TrainerController.start_learning": {
"total": 578.517032638,
"count": 1,
"self": 0.8073510539952622,
"children": {
"TrainerController._reset_env": {
"total": 3.0896110990000807,
"count": 1,
"self": 3.0896110990000807
},
"TrainerController.advance": {
"total": 574.5332795360047,
"count": 18201,
"self": 0.4178188230064279,
"children": {
"env_step": {
"total": 574.1154607129982,
"count": 18201,
"self": 438.22412383298933,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.4827713610058,
"count": 18201,
"self": 2.239021663022754,
"children": {
"TorchPolicy.evaluate": {
"total": 133.24374969798305,
"count": 18201,
"self": 133.24374969798305
}
}
},
"workers": {
"total": 0.4085655190031048,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 576.79598329099,
"count": 18201,
"is_parallel": true,
"self": 272.6075994959831,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006022612000037952,
"count": 1,
"is_parallel": true,
"self": 0.0037124529999346123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00231015900010334,
"count": 10,
"is_parallel": true,
"self": 0.00231015900010334
}
}
},
"UnityEnvironment.step": {
"total": 0.04827466999995522,
"count": 1,
"is_parallel": true,
"self": 0.00070497499996236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005734549999942828,
"count": 1,
"is_parallel": true,
"self": 0.0005734549999942828
},
"communicator.exchange": {
"total": 0.044289417999948455,
"count": 1,
"is_parallel": true,
"self": 0.044289417999948455
},
"steps_from_proto": {
"total": 0.002706822000050124,
"count": 1,
"is_parallel": true,
"self": 0.0004758700000593308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022309519999907934,
"count": 10,
"is_parallel": true,
"self": 0.0022309519999907934
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 304.18838379500687,
"count": 18200,
"is_parallel": true,
"self": 14.016857824024555,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.396570167002437,
"count": 18200,
"is_parallel": true,
"self": 7.396570167002437
},
"communicator.exchange": {
"total": 239.12967704699224,
"count": 18200,
"is_parallel": true,
"self": 239.12967704699224
},
"steps_from_proto": {
"total": 43.645278756987636,
"count": 18200,
"is_parallel": true,
"self": 8.653091226957144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.99218753003049,
"count": 182000,
"is_parallel": true,
"self": 34.99218753003049
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017641199997342483,
"count": 1,
"self": 0.00017641199997342483,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 567.6608743170024,
"count": 783577,
"is_parallel": true,
"self": 17.892159716963874,
"children": {
"process_trajectory": {
"total": 299.5048792680385,
"count": 783577,
"is_parallel": true,
"self": 298.7313824010387,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7734968669998352,
"count": 4,
"is_parallel": true,
"self": 0.7734968669998352
}
}
},
"_update_policy": {
"total": 250.26383533199999,
"count": 90,
"is_parallel": true,
"self": 66.81622740300122,
"children": {
"TorchPPOOptimizer.update": {
"total": 183.44760792899876,
"count": 4587,
"is_parallel": true,
"self": 183.44760792899876
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0866145370000595,
"count": 1,
"self": 0.0011143269998683536,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08550021000019115,
"count": 1,
"self": 0.08550021000019115
}
}
}
}
}
}
}