Ciakon/racesm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

play button wip

Browse Source
This commit is contained in:
Ciakon
2024-04-23 10:44:10 +02:00
parent 8049affcce
commit 89993829ba
8 changed files with 166 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
MLAgents/results/BensonV7/BensonV7.onnx
View File

Binary file not shown.

BIN
MLAgents/results/BensonV7/BensonV7/BensonV7-249156.onnx Normal file
View File

Binary file not shown.

BIN
MLAgents/results/BensonV7/BensonV7/BensonV7-249156.pt Normal file
View File

Binary file not shown.

BIN
MLAgents/results/BensonV7/BensonV7/checkpoint.pt
View File

Binary file not shown.

BIN
MLAgents/results/BensonV7/BensonV7/events.out.tfevents.1713809081.Noahs-Episke-PC.4404.0
View File

Binary file not shown.

BIN
MLAgents/results/BensonV7/BensonV7/events.out.tfevents.1713854673.Noahs-Episke-PC.17592.0 Normal file
View File

Binary file not shown.

312
MLAgents/results/BensonV7/run_logs/timers.json
View File

@@ -2,165 +2,165 @@
"name": "root", "name": "root",
"gauges": { "gauges": {
"BensonV7.Policy.Entropy.mean": { "BensonV7.Policy.Entropy.mean": {
"value": 2.0729053020477295, "value": 1.3791288137435913,
"min": 2.0728888511657715, "min": 1.3791288137435913,
"max": 2.1842892169952393, "max": 2.187758684158325,
"count": 7 "count": 24
}, },
"BensonV7.Policy.Entropy.sum": { "BensonV7.Policy.Entropy.sum": {
"value": 84906.203125, "value": 13763.705078125,
"min": 80925.578125, "min": 13763.705078125,
"max": 89468.484375, "max": 22402.6484375,
"count": 7 "count": 24
}, },
"BensonV7.Step.mean": { "BensonV7.Step.mean": {
"value": 69984.0, "value": 239991.0,
"min": 9984.0, "min": 9984.0,
"max": 69984.0, "max": 239991.0,
"count": 7 "count": 24
}, },
"BensonV7.Step.sum": { "BensonV7.Step.sum": {
"value": 69984.0, "value": 239991.0,
"min": 9984.0, "min": 9984.0,
"max": 69984.0, "max": 239991.0,
"count": 7 "count": 24
}, },
"BensonV7.Policy.ExtrinsicValueEstimate.mean": { "BensonV7.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.10756219178438187, "value": 0.4123384356498718,
"min": -1.984985589981079, "min": -0.17652811110019684,
"max": -0.10756219178438187, "max": 0.4123384356498718,
"count": 7 "count": 24
}, },
"BensonV7.Policy.ExtrinsicValueEstimate.sum": { "BensonV7.Policy.ExtrinsicValueEstimate.sum": {
"value": -26.567861557006836, "value": 75.45793151855469,
"min": -488.30645751953125, "min": -43.4259147644043,
"max": -26.567861557006836, "max": 75.45793151855469,
"count": 7 "count": 24
}, },
"BensonV7.Environment.EpisodeLength.mean": { "BensonV7.Environment.EpisodeLength.mean": {
"value": 81.16216216216216, "value": 208.6595744680851,
"min": 79.0, "min": 79.0,
"max": 81.38866396761134, "max": 208.6595744680851,
"count": 7 "count": 24
}, },
"BensonV7.Environment.EpisodeLength.sum": { "BensonV7.Environment.EpisodeLength.sum": {
"value": 39039.0, "value": 9807.0,
"min": 37920.0, "min": 8690.0,
"max": 41080.0, "max": 10688.0,
"count": 7 "count": 24
}, },
"BensonV7.Self-play.ELO.mean": { "BensonV7.Self-play.ELO.mean": {
"value": 1432.9340303735714, "value": 115.6026867741647,
"min": 1196.0598258059322, "min": 90.04764891469252,
"max": 1432.9340303735714, "max": 1141.217976657289,
"count": 7 "count": 24
}, },
"BensonV7.Self-play.ELO.sum": { "BensonV7.Self-play.ELO.sum": {
"value": 171952.08364482858, "value": 5433.326278385741,
"min": 143527.17909671186, "min": 5433.326278385741,
"max": 180385.31347156668, "max": 136946.1571988747,
"count": 7 "count": 24
}, },
"BensonV7.Environment.CumulativeReward.mean": { "BensonV7.Environment.CumulativeReward.mean": {
"value": -0.09534425969420324, "value": 2.9085576262137773,
"min": -0.11856273706287665, "min": -0.11774942415853053,
"max": -0.035531304608593925, "max": 2.9085576262137773,
"count": 7 "count": 24
}, },
"BensonV7.Environment.CumulativeReward.sum": { "BensonV7.Environment.CumulativeReward.sum": {
"value": -11.536655422998592, "value": 133.79365080583375,
"min": -15.294593081111088, "min": -15.189675716450438,
"max": -4.263756553031271, "max": 133.79365080583375,
"count": 7 "count": 24
}, },
"BensonV7.Policy.ExtrinsicReward.mean": { "BensonV7.Policy.ExtrinsicReward.mean": {
"value": -0.09534425969420324, "value": 2.9085576262137773,
"min": -0.11856273706287665, "min": -0.11774942415853053,
"max": -0.035531304608593925, "max": 2.9085576262137773,
"count": 7 "count": 24
}, },
"BensonV7.Policy.ExtrinsicReward.sum": { "BensonV7.Policy.ExtrinsicReward.sum": {
"value": -11.536655422998592, "value": 133.79365080583375,
"min": -15.294593081111088, "min": -15.189675716450438,
"max": -4.263756553031271, "max": 133.79365080583375,
"count": 7 "count": 24
}, },
"BensonV7.IsTraining.mean": { "BensonV7.IsTraining.mean": {
"value": 1.0, "value": 1.0,
"min": 1.0, "min": 1.0,
"max": 1.0, "max": 1.0,
"count": 7 "count": 24
}, },
"BensonV7.IsTraining.sum": { "BensonV7.IsTraining.sum": {
"value": 1.0, "value": 1.0,
"min": 1.0, "min": 1.0,
"max": 1.0, "max": 1.0,
"count": 7 "count": 24
}, },
"BensonV7.Losses.PolicyLoss.mean": { "BensonV7.Losses.PolicyLoss.mean": {
"value": 0.11715025729667197, "value": 0.11305173472296136,
"min": 0.11001400724555237, "min": 0.0902305781915467,
"max": 0.11715025729667197, "max": 0.1175793781897086,
"count": 6 "count": 23
}, },
"BensonV7.Losses.PolicyLoss.sum": { "BensonV7.Losses.PolicyLoss.sum": {
"value": 0.11715025729667197, "value": 0.11305173472296136,
"min": 0.11001400724555237, "min": 0.0902305781915467,
"max": 0.11715025729667197, "max": 0.1175793781897086,
"count": 6 "count": 23
}, },
"BensonV7.Losses.ValueLoss.mean": { "BensonV7.Losses.ValueLoss.mean": {
"value": 0.0027312553831553743, "value": 0.02714227997847023,
"min": 0.0027312553831553743, "min": 2.293270521482928e-05,
"max": 0.34692010765847486, "max": 0.05294226645212173,
"count": 6 "count": 23
}, },
"BensonV7.Losses.ValueLoss.sum": { "BensonV7.Losses.ValueLoss.sum": {
"value": 0.0027312553831553743, "value": 0.02714227997847023,
"min": 0.0027312553831553743, "min": 2.293270521482928e-05,
"max": 0.34692010765847486, "max": 0.05294226645212173,
"count": 6 "count": 23
}, },
"BensonV7.Policy.LearningRate.mean": { "BensonV7.Policy.LearningRate.mean": {
"value": 0.000299064000312, "value": 0.00029641668119443997,
"min": 0.000299064000312, "min": 0.00029641668119443997,
"max": 0.00029984400005200003, "max": 0.00029984400005200003,
"count": 6 "count": 23
}, },
"BensonV7.Policy.LearningRate.sum": { "BensonV7.Policy.LearningRate.sum": {
"value": 0.000299064000312, "value": 0.00029641668119443997,
"min": 0.000299064000312, "min": 0.00029641668119443997,
"max": 0.00029984400005200003, "max": 0.00029984400005200003,
"count": 6 "count": 23
}, },
"BensonV7.Policy.Epsilon.mean": { "BensonV7.Policy.Epsilon.mean": {
"value": 0.19968800000000003, "value": 0.19880556000000005,
"min": 0.19968800000000003, "min": 0.19880556000000005,
"max": 0.19994800000000001, "max": 0.19994800000000001,
"count": 6 "count": 23
}, },
"BensonV7.Policy.Epsilon.sum": { "BensonV7.Policy.Epsilon.sum": {
"value": 0.19968800000000003, "value": 0.19880556000000005,
"min": 0.19968800000000003, "min": 0.19880556000000005,
"max": 0.19994800000000001, "max": 0.19994800000000001,
"count": 6 "count": 23
}, },
"BensonV7.Policy.Beta.mean": { "BensonV7.Policy.Beta.mean": {
"value": 0.0498440312, "value": 0.049402899444000004,
"min": 0.0498440312, "min": 0.049402899444000004,
"max": 0.049974005200000005, "max": 0.049974005200000005,
"count": 6 "count": 23
}, },
"BensonV7.Policy.Beta.sum": { "BensonV7.Policy.Beta.sum": {
"value": 0.0498440312, "value": 0.049402899444000004,
"min": 0.0498440312, "min": 0.049402899444000004,
"max": 0.049974005200000005, "max": 0.049974005200000005,
"count": 6 "count": 23
} }
}, },
"metadata": { "metadata": {
"timer_format_version": "0.1.0", "timer_format_version": "0.1.0",
"start_time_seconds": "1713809062", "start_time_seconds": "1713854668",
"python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]", "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", "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_version": "0.30.0",
@@ -168,103 +168,103 @@
"communication_protocol_version": "1.5.0", "communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu118", "pytorch_version": "2.2.2+cu118",
"numpy_version": "1.21.2", "numpy_version": "1.21.2",
"end_time_seconds": "1713809367" "end_time_seconds": "1713855170"
}, },
"total": 304.6736262, "total": 502.6965699,
"count": 1, "count": 1,
"self": 0.004877599999929316, "self": 0.004939400000012029,
"children": { "children": {
"run_training.setup": { "run_training.setup": {
"total": 0.0771373999999998, "total": 0.07646299999999995,
"count": 1, "count": 1,
"self": 0.0771373999999998 "self": 0.07646299999999995
}, },
"TrainerController.start_learning": { "TrainerController.start_learning": {
"total": 304.59161120000005, "total": 502.6151675,
"count": 1, "count": 1,
"self": 0.16134309999955576, "self": 0.5009666999978322,
"children": { "children": {
"TrainerController._reset_env": { "TrainerController._reset_env": {
"total": 19.5166619, "total": 5.93716190000001,
"count": 1, "count": 3,
"self": 19.5166619 "self": 5.93716190000001
}, },
"TrainerController.advance": { "TrainerController.advance": {
"total": 284.80744110000046, "total": 496.02484980000213,
"count": 8441, "count": 25454,
"self": 0.15070639999748892, "self": 0.4162786999982018,
"children": { "children": {
"env_step": { "env_step": {
"total": 228.853432300001, "total": 306.42174130000774,
"count": 8441, "count": 25454,
"self": 133.1350660999974, "self": 212.3873840000059,
"children": { "children": {
"SubprocessEnvManager._take_step": { "SubprocessEnvManager._take_step": {
"total": 95.61978480000201, "total": 93.72146940000326,
"count": 8441, "count": 25454,
"self": 1.4240661000022925, "self": 1.258011400004591,
"children": { "children": {
"TorchPolicy.evaluate": { "TorchPolicy.evaluate": {
"total": 94.19571869999972, "total": 92.46345799999867,
"count": 31524, "count": 24958,
"self": 94.19571869999972 "self": 92.46345799999867
} }
} }
}, },
"workers": { "workers": {
"total": 0.09858140000157434, "total": 0.3128878999985645,
"count": 8440, "count": 25454,
"self": 0.0, "self": 0.0,
"children": { "children": {
"worker_root": { "worker_root": {
"total": 272.33989530000036, "total": 493.2314424000014,
"count": 8440, "count": 25454,
"is_parallel": true, "is_parallel": true,
"self": 169.65825009999963, "self": 306.6950511000011,
"children": { "children": {
"steps_from_proto": { "steps_from_proto": {
"total": 0.0013582999999997014, "total": 0.0016319000000137862,
"count": 4, "count": 3,
"is_parallel": true, "is_parallel": true,
"self": 0.0005351000000004547, "self": 0.0005697000000228769,
"children": { "children": {
"_process_rank_one_or_two_observation": { "_process_rank_one_or_two_observation": {
"total": 0.0008231999999992468, "total": 0.0010621999999909093,
"count": 24, "count": 18,
"is_parallel": true, "is_parallel": true,
"self": 0.0008231999999992468 "self": 0.0010621999999909093
} }
} }
}, },
"UnityEnvironment.step": { "UnityEnvironment.step": {
"total": 102.68028690000074, "total": 186.53475940000033,
"count": 8440, "count": 25454,
"is_parallel": true, "is_parallel": true,
"self": 2.971126999999001, "self": 3.401311300002959,
"children": { "children": {
"UnityEnvironment._generate_step_input": { "UnityEnvironment._generate_step_input": {
"total": 3.075714900001067, "total": 3.6382145000039445,
"count": 8440, "count": 25454,
"is_parallel": true, "is_parallel": true,
"self": 3.075714900001067 "self": 3.6382145000039445
}, },
"communicator.exchange": { "communicator.exchange": {
"total": 86.89778070000133, "total": 169.24416609999997,
"count": 8440, "count": 25454,
"is_parallel": true, "is_parallel": true,
"self": 86.89778070000133 "self": 169.24416609999997
}, },
"steps_from_proto": { "steps_from_proto": {
"total": 9.735664299999346, "total": 10.25106749999345,
"count": 33760, "count": 25454,
"is_parallel": true, "is_parallel": true,
"self": 3.697254799999932, "self": 3.835975299991518,
"children": { "children": {
"_process_rank_one_or_two_observation": { "_process_rank_one_or_two_observation": {
"total": 6.038409499999414, "total": 6.415092200001932,
"count": 202560, "count": 152724,
"is_parallel": true, "is_parallel": true,
"self": 6.038409499999414 "self": 6.415092200001932
} }
} }
} }
@@ -277,24 +277,24 @@
} }
}, },
"trainer_advance": { "trainer_advance": {
"total": 55.803302400001996, "total": 189.18682979999616,
"count": 8440, "count": 25454,
"self": 1.1739091000001807, "self": 1.4634836999935033,
"children": { "children": {
"process_trajectory": { "process_trajectory": {
"total": 8.147956200001808, "total": 26.51501530000261,
"count": 8440, "count": 25454,
"self": 8.147956200001808 "self": 26.51501530000261
}, },
"_update_policy": { "_update_policy": {
"total": 46.48143710000001, "total": 161.20833080000006,
"count": 7, "count": 24,
"self": 9.447134400001843, "self": 32.78496999999564,
"children": { "children": {
"TorchPPOOptimizer.update": { "TorchPPOOptimizer.update": {
"total": 37.034302699998165, "total": 128.42336080000442,
"count": 4368, "count": 14628,
"self": 37.034302699998165 "self": 128.42336080000442
} }
} }
} }
@@ -303,19 +303,19 @@
} }
}, },
"trainer_threads": { "trainer_threads": {
"total": 8.000000093488779e-07, "total": 8.999999749903509e-07,
"count": 1, "count": 1,
"self": 8.000000093488779e-07 "self": 8.999999749903509e-07
}, },
"TrainerController._save_models": { "TrainerController._save_models": {
"total": 0.10616430000004584, "total": 0.15218820000001188,
"count": 1, "count": 1,
"self": 0.007284000000026936, "self": 0.007047300000010637,
"children": { "children": {
"RLTrainer._checkpoint": { "RLTrainer._checkpoint": {
"total": 0.0988803000000189, "total": 0.14514090000000124,
"count": 1, "count": 1,
"self": 0.0988803000000189 "self": 0.14514090000000124
} }
} }
} }

20
MLAgents/results/BensonV7/run_logs/training_status.json
View File

@@ -1,24 +1,24 @@
{ {
"BensonV7": { "BensonV7": {
"elo": 1489.2012227625175, "elo": 75.87741801617501,
"checkpoints": [ "checkpoints": [
{ {
"steps": 78400, "steps": 249156,
"file_path": "results\\BensonV7\\BensonV7\\BensonV7-78400.onnx", "file_path": "results\\BensonV7\\BensonV7\\BensonV7-249156.onnx",
"reward": -0.11241376396501437, "reward": null,
"creation_time": 1713809367.0670853, "creation_time": 1713855170.9470267,
"auxillary_file_paths": [ "auxillary_file_paths": [
"results\\BensonV7\\BensonV7\\BensonV7-78400.pt" "results\\BensonV7\\BensonV7\\BensonV7-249156.pt"
] ]
} }
], ],
"final_checkpoint": { "final_checkpoint": {
"steps": 78400, "steps": 249156,
"file_path": "results\\BensonV7\\BensonV7.onnx", "file_path": "results\\BensonV7\\BensonV7.onnx",
"reward": -0.11241376396501437, "reward": null,
"creation_time": 1713809367.0670853, "creation_time": 1713855170.9470267,
"auxillary_file_paths": [ "auxillary_file_paths": [
"results\\BensonV7\\BensonV7\\BensonV7-78400.pt" "results\\BensonV7\\BensonV7\\BensonV7-249156.pt"
] ]
} }
}, },