Goldtroz

Goldtroz/amd-rl-lab

Reinforcement learning on AMD GPUs — PPO, SAC, custom envs, RLHF

11 stars 0 forks 11 watchers Python MIT License

open-source ppo python rocm sac

1 Open Issue Need Help Last updated: Jul 6, 2026

Open Issues Need Help

View All on GitHub

Bug: PPO training diverges on continuous action spaces about 6 hours ago

help wanted good first issue question

Goldtroz/amd-rl-lab

11

Reinforcement learning on AMD GPUs — PPO, SAC, custom envs, RLHF

Python

#open-source#ppo#python#rocm#sac