benson V6 har smadret racetrack 1

This commit is contained in:
2024-04-20 17:04:19 +02:00
parent 65607aebc4
commit d5b24b17ea
37 changed files with 134577 additions and 605 deletions

View File

@@ -1,5 +1,5 @@
behaviors:
BensonV5:
BensonV6:
trainer_type: ppo
hyperparameters:

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -0,0 +1,76 @@
default_settings: null
behaviors:
BensonV6:
trainer_type: ppo
hyperparameters:
batch_size: 50
buffer_size: 10240
learning_rate: 0.0003
beta: 0.05
epsilon: 0.2
lambd: 0.95
num_epoch: 3
shared_critic: false
learning_rate_schedule: linear
beta_schedule: linear
epsilon_schedule: linear
network_settings:
normalize: false
hidden_units: 128
num_layers: 2
vis_encode_type: simple
memory: null
goal_conditioning_type: hyper
deterministic: false
reward_signals:
extrinsic:
gamma: 0.99
strength: 1.0
network_settings:
normalize: false
hidden_units: 128
num_layers: 2
vis_encode_type: simple
memory: null
goal_conditioning_type: hyper
deterministic: false
init_path: null
keep_checkpoints: 5
checkpoint_interval: 500000
max_steps: 3000000
time_horizon: 64
summary_freq: 10000
threaded: false
self_play: null
behavioral_cloning: null
env_settings:
env_path: null
env_args: null
base_port: 5005
num_envs: 1
num_areas: 1
seed: -1
max_lifetime_restarts: 10
restarts_rate_limit_n: 1
restarts_rate_limit_period_s: 60
engine_settings:
width: 84
height: 84
quality_level: 5
time_scale: 20
target_frame_rate: -1
capture_frame_rate: 60
no_graphics: false
environment_parameters: null
checkpoint_settings:
run_id: BensonV6
initialize_from: null
load_model: false
resume: false
force: true
train_model: false
inference: false
results_dir: results
torch_settings:
device: null
debug: false

View File

@@ -0,0 +1,313 @@
{
"name": "root",
"gauges": {
"BensonV6.Policy.Entropy.mean": {
"value": 1.5862776041030884,
"min": 1.365457534790039,
"max": 2.193558931350708,
"count": 33
},
"BensonV6.Policy.Entropy.sum": {
"value": 15957.9521484375,
"min": 13736.5029296875,
"max": 22374.30078125,
"count": 33
},
"BensonV6.Environment.EpisodeLength.mean": {
"value": 230.2325581395349,
"min": 59.56547619047619,
"max": 345.2,
"count": 33
},
"BensonV6.Environment.EpisodeLength.sum": {
"value": 9900.0,
"min": 8960.0,
"max": 11034.0,
"count": 33
},
"BensonV6.Step.mean": {
"value": 329973.0,
"min": 9995.0,
"max": 329973.0,
"count": 33
},
"BensonV6.Step.sum": {
"value": 329973.0,
"min": 9995.0,
"max": 329973.0,
"count": 33
},
"BensonV6.Policy.ExtrinsicValueEstimate.mean": {
"value": 5.722393989562988,
"min": 0.2746765613555908,
"max": 5.809690475463867,
"count": 33
},
"BensonV6.Policy.ExtrinsicValueEstimate.sum": {
"value": 989.97412109375,
"min": 46.69501495361328,
"max": 1022.5054931640625,
"count": 33
},
"BensonV6.Environment.CumulativeReward.mean": {
"value": 19.246166612901508,
"min": -0.019117560070522267,
"max": 23.05193606035318,
"count": 33
},
"BensonV6.Environment.CumulativeReward.sum": {
"value": 827.5851643547649,
"min": -3.1161622914951295,
"max": 922.0774424141273,
"count": 33
},
"BensonV6.Policy.ExtrinsicReward.mean": {
"value": 19.246166612901508,
"min": -0.019117560070522267,
"max": 23.05193606035318,
"count": 33
},
"BensonV6.Policy.ExtrinsicReward.sum": {
"value": 827.5851643547649,
"min": -3.1161622914951295,
"max": 922.0774424141273,
"count": 33
},
"BensonV6.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"BensonV6.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"BensonV6.Losses.PolicyLoss.mean": {
"value": 0.11866796751207544,
"min": 0.0957306937479255,
"max": 0.12068313519878321,
"count": 32
},
"BensonV6.Losses.PolicyLoss.sum": {
"value": 0.11866796751207544,
"min": 0.0957306937479255,
"max": 0.12068313519878321,
"count": 32
},
"BensonV6.Losses.ValueLoss.mean": {
"value": 0.6118914237836512,
"min": 0.021924442883459776,
"max": 0.7137479831288064,
"count": 32
},
"BensonV6.Losses.ValueLoss.sum": {
"value": 0.6118914237836512,
"min": 0.021924442883459776,
"max": 0.7137479831288064,
"count": 32
},
"BensonV6.Policy.LearningRate.mean": {
"value": 0.00026712281095906667,
"min": 0.00026712281095906667,
"max": 0.00029897050034316655,
"count": 32
},
"BensonV6.Policy.LearningRate.sum": {
"value": 0.00026712281095906667,
"min": 0.00026712281095906667,
"max": 0.00029897050034316655,
"count": 32
},
"BensonV6.Policy.Epsilon.mean": {
"value": 0.18904093333333336,
"min": 0.18904093333333336,
"max": 0.19965683333333328,
"count": 32
},
"BensonV6.Policy.Epsilon.sum": {
"value": 0.18904093333333336,
"min": 0.18904093333333336,
"max": 0.19965683333333328,
"count": 32
},
"BensonV6.Policy.Beta.mean": {
"value": 0.04452156257333334,
"min": 0.04452156257333334,
"max": 0.049828450983333335,
"count": 32
},
"BensonV6.Policy.Beta.sum": {
"value": 0.04452156257333334,
"min": 0.04452156257333334,
"max": 0.049828450983333335,
"count": 32
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1713623140",
"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/BensonV6.yaml --run-id=BensonV6 --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": "1713623853"
},
"total": 712.8463069000001,
"count": 1,
"self": 0.00745920000008482,
"children": {
"run_training.setup": {
"total": 0.07786059999999995,
"count": 1,
"self": 0.07786059999999995
},
"TrainerController.start_learning": {
"total": 712.7609871,
"count": 1,
"self": 0.7619565000039756,
"children": {
"TrainerController._reset_env": {
"total": 5.778238099999999,
"count": 1,
"self": 5.778238099999999
},
"TrainerController.advance": {
"total": 706.039172599996,
"count": 34801,
"self": 0.612005799983308,
"children": {
"env_step": {
"total": 415.03360060000045,
"count": 34801,
"self": 265.1050452999982,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.45768900000039,
"count": 34801,
"self": 2.116340399996801,
"children": {
"TorchPolicy.evaluate": {
"total": 147.34134860000358,
"count": 33434,
"self": 147.34134860000358
}
}
},
"workers": {
"total": 0.47086630000189267,
"count": 34800,
"self": 0.0,
"children": {
"worker_root": {
"total": 706.6658678000041,
"count": 34800,
"is_parallel": true,
"self": 482.1807981999955,
"children": {
"steps_from_proto": {
"total": 0.0005944000000006611,
"count": 1,
"is_parallel": true,
"self": 0.00020790000000125985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003864999999994012,
"count": 6,
"is_parallel": true,
"self": 0.0003864999999994012
}
}
},
"UnityEnvironment.step": {
"total": 224.4844752000086,
"count": 34800,
"is_parallel": true,
"self": 5.25407010000518,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.428810699995278,
"count": 34800,
"is_parallel": true,
"self": 5.428810699995278
},
"communicator.exchange": {
"total": 198.2789811000104,
"count": 34800,
"is_parallel": true,
"self": 198.2789811000104
},
"steps_from_proto": {
"total": 15.522613299997753,
"count": 34800,
"is_parallel": true,
"self": 5.879353500006703,
"children": {
"_process_rank_one_or_two_observation": {
"total": 9.64325979999105,
"count": 208800,
"is_parallel": true,
"self": 9.64325979999105
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 290.3935662000123,
"count": 34800,
"self": 1.3219589000069618,
"children": {
"process_trajectory": {
"total": 40.38120300000543,
"count": 34800,
"self": 40.38120300000543
},
"_update_policy": {
"total": 248.69040429999993,
"count": 32,
"self": 46.19149409999946,
"children": {
"TorchPPOOptimizer.update": {
"total": 202.49891020000047,
"count": 19674,
"self": 202.49891020000047
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6999999843392288e-06,
"count": 1,
"self": 1.6999999843392288e-06
},
"TrainerController._save_models": {
"total": 0.18161820000000262,
"count": 1,
"self": 0.011474000000021078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17014419999998154,
"count": 1,
"self": 0.17014419999998154
}
}
}
}
}
}
}

View File

@@ -0,0 +1,29 @@
{
"BensonV6": {
"checkpoints": [
{
"steps": 334006,
"file_path": "results\\BensonV6\\BensonV6\\BensonV6-334006.onnx",
"reward": 17.643121887110173,
"creation_time": 1713623853.1815405,
"auxillary_file_paths": [
"results\\BensonV6\\BensonV6\\BensonV6-334006.pt"
]
}
],
"final_checkpoint": {
"steps": 334006,
"file_path": "results\\BensonV6\\BensonV6.onnx",
"reward": 17.643121887110173,
"creation_time": 1713623853.1815405,
"auxillary_file_paths": [
"results\\BensonV6\\BensonV6\\BensonV6-334006.pt"
]
}
},
"metadata": {
"stats_format_version": "0.3.0",
"mlagents_version": "0.30.0",
"torch_version": "2.2.2+cu118"
}
}

View File

@@ -1,2 +1,2 @@
mlagents-learn config/BensonV6.yaml --run-id=BensonV6 --resume
mlagents-learn config/BensonV6.yaml --run-id=BensonV6.1 --force
@REM mlagents-learn config/BensonV5.yaml --run-id=BensonV5 --resume --env="C:\Users\noahk\Desktop\BensonV5\Racesm_L.exe" --no-graphics --num-envs=1