Playing Pok'emon Red via Deep Reinforcement Learning

2025-02-27

AI Summary

研究解决《Pokémon Red》游戏中多任务、长时程、探索难和策略多样性的问题，采用深度强化学习方法训练智能体完成初始游戏阶段。

Technology Category

• Machine Learning: Reinforcement Learning
• Multiagent Systems: Distributed Problem Solving
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Pok'emon Red, a classic Game Boy JRPG, presents significant challenges as a testbed for agents, including multi-tasking, long horizons of tens of thousands of steps, hard exploration, and a vast array of potential policies. We introduce a simplistic environment and a Deep Reinforcement Learning (DRL) training methodology, demonstrating a baseline agent that completes an initial segment of the game up to completing Cerulean City. Our experiments include various ablations that reveal vulnerabilities in reward shaping, where agents exploit specific reward signals. We also discuss limitations and argue that games like Pok'emon hold strong potential for future research on Large Language Model agents, hierarchical training algorithms, and advanced exploration methods. Source Code: https://github.com/MarcoMeter/neroRL/tree/poke_red

Problem

• Challenges in multi-tasking and long horizons
• Exploration of reward shaping vulnerabilities
• Potential for future research on advanced methods

Innovation

• Deep Reinforcement Learning methodology
• Simplistic environment creation
• Reward shaping vulnerabilities analysis