Head-to-head evaluation for RL policies in video games.
Micro-State-Space is a research-driven collection of compact strategy environments featuring Hex-Line, Quantum Match, and Shift-3. It explores deterministic state spaces using MCTS, alpha-beta search, and tabular reinforcement learning, providing interactive Streamlit apps, visual analysis, and agent serialization.
AlphaZero implementation from scratch, self-play RL with MCTS and ResNet, trained on Connect4
Various poker AI algorithms. MARL, Self Play, CFR
AIM (Autonomous Intelligent Model) is a dual-engine Rubik’s Cube intelligence system that unifies classical algorithmic solving with modern reinforcement learning research. It is not just a cube solver— it is a simulation lab, built for experimentation, visualization, optimization, and AI behavior analysis. AIM provides: ⚡ A high-performance sol
A specialized Reinforcement Learning (RL) project focused on multi-task mastery across 10 distinct gaming environments. General-Gamer-AI-Lite implements a lightweight multi-task agent designed to learn shared representations and transfer knowledge between varied game mechanics, from classic arcade challenges to strategic grid worlds.
To associate your repository with the self-play-rl topic, visit your repo's landing page and select "manage topics."