self learning test
This commit is contained in:
325
MLAgents/results/BensonV7/run_logs/timers.json
Normal file
325
MLAgents/results/BensonV7/run_logs/timers.json
Normal file
@@ -0,0 +1,325 @@
|
||||
{
|
||||
"name": "root",
|
||||
"gauges": {
|
||||
"BensonV7.Policy.Entropy.mean": {
|
||||
"value": 2.0729053020477295,
|
||||
"min": 2.0728888511657715,
|
||||
"max": 2.1842892169952393,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Policy.Entropy.sum": {
|
||||
"value": 84906.203125,
|
||||
"min": 80925.578125,
|
||||
"max": 89468.484375,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Step.mean": {
|
||||
"value": 69984.0,
|
||||
"min": 9984.0,
|
||||
"max": 69984.0,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Step.sum": {
|
||||
"value": 69984.0,
|
||||
"min": 9984.0,
|
||||
"max": 69984.0,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Policy.ExtrinsicValueEstimate.mean": {
|
||||
"value": -0.10756219178438187,
|
||||
"min": -1.984985589981079,
|
||||
"max": -0.10756219178438187,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Policy.ExtrinsicValueEstimate.sum": {
|
||||
"value": -26.567861557006836,
|
||||
"min": -488.30645751953125,
|
||||
"max": -26.567861557006836,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Environment.EpisodeLength.mean": {
|
||||
"value": 81.16216216216216,
|
||||
"min": 79.0,
|
||||
"max": 81.38866396761134,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Environment.EpisodeLength.sum": {
|
||||
"value": 39039.0,
|
||||
"min": 37920.0,
|
||||
"max": 41080.0,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Self-play.ELO.mean": {
|
||||
"value": 1432.9340303735714,
|
||||
"min": 1196.0598258059322,
|
||||
"max": 1432.9340303735714,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Self-play.ELO.sum": {
|
||||
"value": 171952.08364482858,
|
||||
"min": 143527.17909671186,
|
||||
"max": 180385.31347156668,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Environment.CumulativeReward.mean": {
|
||||
"value": -0.09534425969420324,
|
||||
"min": -0.11856273706287665,
|
||||
"max": -0.035531304608593925,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Environment.CumulativeReward.sum": {
|
||||
"value": -11.536655422998592,
|
||||
"min": -15.294593081111088,
|
||||
"max": -4.263756553031271,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Policy.ExtrinsicReward.mean": {
|
||||
"value": -0.09534425969420324,
|
||||
"min": -0.11856273706287665,
|
||||
"max": -0.035531304608593925,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Policy.ExtrinsicReward.sum": {
|
||||
"value": -11.536655422998592,
|
||||
"min": -15.294593081111088,
|
||||
"max": -4.263756553031271,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.IsTraining.mean": {
|
||||
"value": 1.0,
|
||||
"min": 1.0,
|
||||
"max": 1.0,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.IsTraining.sum": {
|
||||
"value": 1.0,
|
||||
"min": 1.0,
|
||||
"max": 1.0,
|
||||
"count": 7
|
||||
},
|
||||
"BensonV7.Losses.PolicyLoss.mean": {
|
||||
"value": 0.11715025729667197,
|
||||
"min": 0.11001400724555237,
|
||||
"max": 0.11715025729667197,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Losses.PolicyLoss.sum": {
|
||||
"value": 0.11715025729667197,
|
||||
"min": 0.11001400724555237,
|
||||
"max": 0.11715025729667197,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Losses.ValueLoss.mean": {
|
||||
"value": 0.0027312553831553743,
|
||||
"min": 0.0027312553831553743,
|
||||
"max": 0.34692010765847486,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Losses.ValueLoss.sum": {
|
||||
"value": 0.0027312553831553743,
|
||||
"min": 0.0027312553831553743,
|
||||
"max": 0.34692010765847486,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Policy.LearningRate.mean": {
|
||||
"value": 0.000299064000312,
|
||||
"min": 0.000299064000312,
|
||||
"max": 0.00029984400005200003,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Policy.LearningRate.sum": {
|
||||
"value": 0.000299064000312,
|
||||
"min": 0.000299064000312,
|
||||
"max": 0.00029984400005200003,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Policy.Epsilon.mean": {
|
||||
"value": 0.19968800000000003,
|
||||
"min": 0.19968800000000003,
|
||||
"max": 0.19994800000000001,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Policy.Epsilon.sum": {
|
||||
"value": 0.19968800000000003,
|
||||
"min": 0.19968800000000003,
|
||||
"max": 0.19994800000000001,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Policy.Beta.mean": {
|
||||
"value": 0.0498440312,
|
||||
"min": 0.0498440312,
|
||||
"max": 0.049974005200000005,
|
||||
"count": 6
|
||||
},
|
||||
"BensonV7.Policy.Beta.sum": {
|
||||
"value": 0.0498440312,
|
||||
"min": 0.0498440312,
|
||||
"max": 0.049974005200000005,
|
||||
"count": 6
|
||||
}
|
||||
},
|
||||
"metadata": {
|
||||
"timer_format_version": "0.1.0",
|
||||
"start_time_seconds": "1713809062",
|
||||
"python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]",
|
||||
"command_line_arguments": "C:\\Users\\noahk\\Documents\\Unity projects\\Racesm\\.venv\\Scripts\\mlagents-learn config/BensonV7.yaml --run-id=BensonV7 --force",
|
||||
"mlagents_version": "0.30.0",
|
||||
"mlagents_envs_version": "0.30.0",
|
||||
"communication_protocol_version": "1.5.0",
|
||||
"pytorch_version": "2.2.2+cu118",
|
||||
"numpy_version": "1.21.2",
|
||||
"end_time_seconds": "1713809367"
|
||||
},
|
||||
"total": 304.6736262,
|
||||
"count": 1,
|
||||
"self": 0.004877599999929316,
|
||||
"children": {
|
||||
"run_training.setup": {
|
||||
"total": 0.0771373999999998,
|
||||
"count": 1,
|
||||
"self": 0.0771373999999998
|
||||
},
|
||||
"TrainerController.start_learning": {
|
||||
"total": 304.59161120000005,
|
||||
"count": 1,
|
||||
"self": 0.16134309999955576,
|
||||
"children": {
|
||||
"TrainerController._reset_env": {
|
||||
"total": 19.5166619,
|
||||
"count": 1,
|
||||
"self": 19.5166619
|
||||
},
|
||||
"TrainerController.advance": {
|
||||
"total": 284.80744110000046,
|
||||
"count": 8441,
|
||||
"self": 0.15070639999748892,
|
||||
"children": {
|
||||
"env_step": {
|
||||
"total": 228.853432300001,
|
||||
"count": 8441,
|
||||
"self": 133.1350660999974,
|
||||
"children": {
|
||||
"SubprocessEnvManager._take_step": {
|
||||
"total": 95.61978480000201,
|
||||
"count": 8441,
|
||||
"self": 1.4240661000022925,
|
||||
"children": {
|
||||
"TorchPolicy.evaluate": {
|
||||
"total": 94.19571869999972,
|
||||
"count": 31524,
|
||||
"self": 94.19571869999972
|
||||
}
|
||||
}
|
||||
},
|
||||
"workers": {
|
||||
"total": 0.09858140000157434,
|
||||
"count": 8440,
|
||||
"self": 0.0,
|
||||
"children": {
|
||||
"worker_root": {
|
||||
"total": 272.33989530000036,
|
||||
"count": 8440,
|
||||
"is_parallel": true,
|
||||
"self": 169.65825009999963,
|
||||
"children": {
|
||||
"steps_from_proto": {
|
||||
"total": 0.0013582999999997014,
|
||||
"count": 4,
|
||||
"is_parallel": true,
|
||||
"self": 0.0005351000000004547,
|
||||
"children": {
|
||||
"_process_rank_one_or_two_observation": {
|
||||
"total": 0.0008231999999992468,
|
||||
"count": 24,
|
||||
"is_parallel": true,
|
||||
"self": 0.0008231999999992468
|
||||
}
|
||||
}
|
||||
},
|
||||
"UnityEnvironment.step": {
|
||||
"total": 102.68028690000074,
|
||||
"count": 8440,
|
||||
"is_parallel": true,
|
||||
"self": 2.971126999999001,
|
||||
"children": {
|
||||
"UnityEnvironment._generate_step_input": {
|
||||
"total": 3.075714900001067,
|
||||
"count": 8440,
|
||||
"is_parallel": true,
|
||||
"self": 3.075714900001067
|
||||
},
|
||||
"communicator.exchange": {
|
||||
"total": 86.89778070000133,
|
||||
"count": 8440,
|
||||
"is_parallel": true,
|
||||
"self": 86.89778070000133
|
||||
},
|
||||
"steps_from_proto": {
|
||||
"total": 9.735664299999346,
|
||||
"count": 33760,
|
||||
"is_parallel": true,
|
||||
"self": 3.697254799999932,
|
||||
"children": {
|
||||
"_process_rank_one_or_two_observation": {
|
||||
"total": 6.038409499999414,
|
||||
"count": 202560,
|
||||
"is_parallel": true,
|
||||
"self": 6.038409499999414
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"trainer_advance": {
|
||||
"total": 55.803302400001996,
|
||||
"count": 8440,
|
||||
"self": 1.1739091000001807,
|
||||
"children": {
|
||||
"process_trajectory": {
|
||||
"total": 8.147956200001808,
|
||||
"count": 8440,
|
||||
"self": 8.147956200001808
|
||||
},
|
||||
"_update_policy": {
|
||||
"total": 46.48143710000001,
|
||||
"count": 7,
|
||||
"self": 9.447134400001843,
|
||||
"children": {
|
||||
"TorchPPOOptimizer.update": {
|
||||
"total": 37.034302699998165,
|
||||
"count": 4368,
|
||||
"self": 37.034302699998165
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"trainer_threads": {
|
||||
"total": 8.000000093488779e-07,
|
||||
"count": 1,
|
||||
"self": 8.000000093488779e-07
|
||||
},
|
||||
"TrainerController._save_models": {
|
||||
"total": 0.10616430000004584,
|
||||
"count": 1,
|
||||
"self": 0.007284000000026936,
|
||||
"children": {
|
||||
"RLTrainer._checkpoint": {
|
||||
"total": 0.0988803000000189,
|
||||
"count": 1,
|
||||
"self": 0.0988803000000189
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
30
MLAgents/results/BensonV7/run_logs/training_status.json
Normal file
30
MLAgents/results/BensonV7/run_logs/training_status.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"BensonV7": {
|
||||
"elo": 1489.2012227625175,
|
||||
"checkpoints": [
|
||||
{
|
||||
"steps": 78400,
|
||||
"file_path": "results\\BensonV7\\BensonV7\\BensonV7-78400.onnx",
|
||||
"reward": -0.11241376396501437,
|
||||
"creation_time": 1713809367.0670853,
|
||||
"auxillary_file_paths": [
|
||||
"results\\BensonV7\\BensonV7\\BensonV7-78400.pt"
|
||||
]
|
||||
}
|
||||
],
|
||||
"final_checkpoint": {
|
||||
"steps": 78400,
|
||||
"file_path": "results\\BensonV7\\BensonV7.onnx",
|
||||
"reward": -0.11241376396501437,
|
||||
"creation_time": 1713809367.0670853,
|
||||
"auxillary_file_paths": [
|
||||
"results\\BensonV7\\BensonV7\\BensonV7-78400.pt"
|
||||
]
|
||||
}
|
||||
},
|
||||
"metadata": {
|
||||
"stats_format_version": "0.3.0",
|
||||
"mlagents_version": "0.30.0",
|
||||
"torch_version": "2.2.2+cu118"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user