Martin Kubovčík

Train transformer language models with reinforcement learning.

Reinforcement Learning project training PPO agents on Atari, Retro (Sonic, Mario) or classic environments using Stable Baselines 3, featuring dataset generation and WanDB experiment tracking.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)