tmrl
tmrl copied to clipboard
Reinforcement Learning for real-time applications - host of the TrackMania Roborace League
As mentionned in the title, the program doesn't seem to use my NVIDIA GPU (3050 ti) to train. Instead, CPU usage jumps to 100% ![TMRL result](https://user-images.githubusercontent.com/39390866/180462505-a755059d-38ee-4003-a916-80c54600e9c9.png)
Added fix for scaled desktops. When Windows is scaled in the display settings, the script won't detect the edges of the Trackmania window properly. This fix makes the script makes...
i have be try to record a reward on track ![Screenshot 2024-04-26 185119](https://github.com/trackmania-rl/tmrl/assets/86875051/c1e790c5-f80b-4c4c-a343-b228418a98a4) ![Screenshot 2024-04-26 185200](https://github.com/trackmania-rl/tmrl/assets/86875051/cb9ff10f-e98f-4700-80d4-6bed93fda82a) Later, when I attempted to run the check environment, all of the errors disappeared....
``` C:\Windows\System32>python -m tmrl --test INFO:numexpr.utils:Note: NumExpr detected 16 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. INFO:numexpr.utils:NumExpr defaulting to 8 threads. INFO:root:Namespace(server=False, trainer=False, worker=False, test=True, benchmark=False,...
When I try to turn "interface_kwargs": {"save_replays": false} in config.json to true,the worker doesn't control car and throw out [WinError 10061]. My OpenPlanet version is 1.26.25 My tmrl version is...
Dear author, I am a graduate student, and I want to use parallel genetic algorithm to train my racing AI, so I read your article. I have to say that...
This should be mentioned in the readme somewhere.