paper-with-me

Papers

4Hammer: a board-game reinforcement learning environment for the hour long time frame

2025-05-19 · Massimo Fioravanti, Giovanni Agosta

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.

📄 PDF Abstract BibTeX arXiv:2505.13638

Code (2)

rl-language/4hammer 공식 구현
rl-language/rlc 공식 구현

Tasks

Board Gamesreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning

2025-07-09 · Matej Straka, Martin Schmid

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 Learning

Towards automating Codenames spymasters with deep reinforcement learning

2022-12-28 · Sherman Siu

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)+1

Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales

2020-01-29 · Sam Earle

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 Learning

Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games

2026-02-11 · Kazuki Ota, Takayuki Osa, Motoki Omura, Tatsuya Harada arxiv

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 Learning

A Technique to Create Weaker Abstract Board Game Agents via Reinforcement Learning

2022-09-01 · Peter Jamieson, Indrima Upadhyay

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)