用强化学习设计文本游戏智能体，显著提升通关率和胜率。
Design and Optimization of Reinforcement Learning-Based Agents in Text-Based Games
- 用深度学习构建世界模型，解析游戏文本
- 基于策略梯度方法训练智能体，实现状态到最优动作的映射
- 在多个文本游戏中表现超越以往方法，适合通用智能体研究
随着人工智能技术的发展，利用智能体玩文本游戏的研究日益受到关注。本文提出一种基于强化学习的智能体设计与学习新方法。首先采用深度学习模型处理游戏文本并构建世界模型；随后，通过基于策略梯度的深度强化学习方法训练智能体，实现从状态价值到最优策略的转化。在多个文本游戏实验中，优化后的智能体表现更优，游戏完成率和胜率显著高于以往方法。本研究为强化学习应用于文本游戏提供了新的理解与实证基础，并为开发和优化适用于更广泛领域和问题的强化学习智能体奠定了基础。
原文摘要 · Abstract (English)
As AI technology advances, research in playing text-based games with agents has becomeprogressively popular. In this paper, a novel approach to agent design and agent learning ispresented with the context of reinforcement learning. A model of deep learning is first applied toprocess game text and build a world model. Next, the agent is learned through a policy gradient-based deep reinforcement learning method to facilitate conversion from state value to optimal policy.The enhanced agent works better in several text-based game experiments and significantlysurpasses previous agents on game completion ratio and win rate. Our study introduces novelunderstanding and empirical ground for using reinforcement learning for text games and sets thestage for developing and optimizing reinforcement learning agents for more general domains andproblems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。