World model on a Boolean hypercube: frozen reservoir encoders and a locally connected predictor that learns how the latent code moves under an action. C++20, no dependencies.
ReinforceUI-Studio. A Python-based application designed to simplify the configuration and monitoring of RL training processes. Supporting MuJoCo, OpenAI Gymnasium, and DeepMind Control Suite. Algorithms included: CTD4, DDPG, DQN, PPO, SAC, TD3, TQC
