Explore live open-source projects and AI models.

Code for PuzzleJAX, a benchmark for reasoning and learning, that reimplements PuzzleScript, a concise and expressive DSL and game engine for grid-based puzzle games, in JAX.

🕵 Code for our EMNLP 2025 Main paper: "FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games"

IIG-RL-Benchmark is a library for training and evaluating game theoretical or deep RL algorithms on OpenSpiel games.

Examples and presentation for Pacific++/MeetingC++ talk "Benchmarking C++. From video games to algorithmic trading"

Code for the paper "Accelerating Probabilistic Planning Research: High-Speed Implementations of Stochastic Markov Decision Processes and Their Catalogization"

[COG24] - Official repository of "OfflineMania: A Benchmark Environment for Offline Reinforcement Learning in Racing Games"

War Games measures whether frontier models can sustain long-horizon planning and adaptation in complex, non-stationary real-time games, with human performance as the benchmark.