LuckyMera: a Modular AI Framework for Building Hybrid NetHack Agents
In the last few decades we have witnessed a significant development in Artificial Intelligence (AI) thanks to the availability of a variety of testbeds, mostly based on simulated environments and video games. Among those, roguelike games offer a very good trade-off in terms of complexity of the environment and computational costs, which makes them perfectly suited to test AI agents generalization capabilities. In this work, we present LuckyMera, a flexible, modular, extensible and configurable AI framework built around NetHack, a popular terminal-based, single-player roguelike video game. This library is aimed at simplifying and speeding up the development of AI agents capable of successfully playing the game and offering a high-level interface for designing game strategies. LuckyMera comes with a set of off-the-shelf symbolic and neural modules (called "skills"): these modules can be either hard-coded behaviors, or neural Reinforcement Learning approaches, with the possibility of creating compositional hybrid solutions. Additionally, LuckyMera comes with a set of utility features to save its experiences in the form of trajectories for further analysis and to use them as datasets to train neural modules, with a direct interface to the NetHack Learning Environment and MiniHack. Through an empirical evaluation we validate our skills implementation and propose a strong baseline agent that can reach state-of-the-art performances in the complete NetHack game. LuckyMera is open-source and available at https://github.com/Pervasive-AI-Lab/LuckyMera.
Code (1)
Tasks
NetHackMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Insights From the NeurIPS 2021 NetHack Challenge
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of N…
NetHackReinforcement Learning (RL)Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents
Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightf…
Decision MakingMinecraftNetHackDungeons and Data: A Large-Scale NetHack Dataset
Recent breakthroughs in the development of agents to solve challenging sequential decision making problems such as Go, StarCraft, or DOTA, have relied on both simulated environments and large-scale datasets. However, pro…
Decision MakingNetHackOffline RLSequential Decision Making+1The NetHack Learning Environment
Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently comple…
NetHackNetHack ScoreReinforcement Learning (RL)Systematic GeneralizationNetHack is Hard to Hack
Neural policy learning methods have achieved remarkable results in various control problems, ranging from Atari games to simulated locomotion. However, these methods struggle in long-horizon tasks, especially in open-end…