4Hammer: a board-game reinforcement learning environment for the hour long time frame
Large Language Models (LLMs) have demonstrated strong performance on tasks with short time frames, but struggle with tasks requiring longer durations. While datasets covering extended-duration tasks, such as software engineering tasks or video games, do exist, there are currently few implementations of complex board games specifically designed for reinforcement learning and LLM evaluation. To address this gap, we propose the 4Hammer reinforcement learning environment, a digital twin simulation of a subset of Warhammer 40,000-a complex, zero-sum board game. Warhammer 40,000 features intricate rules, requiring human players to thoroughly read and understand over 50 pages of detailed natural language rules, grasp the interactions between their game pieces and those of their opponents, and independently track and communicate the evolving game state.
Code (2)
Tasks
Board Gamesreinforcement-learningReinforcement LearningSimilar Papers 제목 키워드 기반
Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning
We introduce a real-time strategy game environment built on Generals.io, a game that hosts thousands of active players each week across multiple game formats. Our environment is fully compatible with Gymnasium and Pettin…
GPUMulti-agent Reinforcement Learningreinforcement-learningReinforcement LearningTowards automating Codenames spymasters with deep reinforcement learning
Although most reinforcement learning research has centered on competitive games, little work has been done on applying it to co-operative multiplayer games or text-based games. Codenames is a board game that involves bot…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales
We introduce gym-city, a Reinforcement Learning environment that uses SimCity 1's game engine to simulate an urban environment, wherein agents might seek to optimize one or a combination of any number of city-wide metric…
Reinforcement LearningRevisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
Two-player games such as board games have long been used as traditional benchmarks for reinforcement learning. This work revisits a policy optimization method with reverse Kullback-Leibler regularization and entropy regu…
Reinforcement LearningA Technique to Create Weaker Abstract Board Game Agents via Reinforcement Learning
Board games, with the exception of solo games, need at least one other player to play. Because of this, we created Artificial Intelligent (AI) agents to play against us when an opponent is missing. These AI agents are cr…
Board GamesQ-Learningreinforcement-learningReinforcement Learning (RL)