It's designed to be educational, not production-ready. Use it to understand how RL environments work, experiment with reward functions, and see reward hacking in action. pokemon-rl-env/ ├── ...

Pokemon Showdown multi-agent RL environment for prime-rl. Enables training LLMs to play competitive Pokemon via GRPO, with turn-by-turn control, self-play, and configurable rewards. Layer 4: ...

Reinforcement learning is a method of learning actions to maximize a set reward as an objective, and is commonly used in AI for shogi and go. Rather than relying on a ...