PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models

TL;DR

PokeLLMon is a novel LLM-based agent that achieves human-parity in Pokemon battles by combining in-context reinforcement learning, knowledge retrieval, and consistent action generation, demonstrating competitive win rates against humans.

Contribution

This paper introduces PokeLLMon, the first LLM-embodied agent capable of human-parity performance in tactical Pokemon battles, integrating multiple strategies for improved decision-making.

Findings

Achieves 49% win rate in Ladder competitions

Achieves 56% win rate in invited battles

Demonstrates human-like battle strategies and decision-making

Abstract

We introduce PokeLLMon, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pokemon battles. The design of PokeLLMon incorporates three key strategies: (i) In-context reinforcement learning that instantly consumes text-based feedback derived from battles to iteratively refine the policy; (ii) Knowledge-augmented generation that retrieves external knowledge to counteract hallucination and enables the agent to act timely and properly; (iii) Consistent action generation to mitigate the panic switching phenomenon when the agent faces a powerful opponent and wants to elude the battle. We show that online battles against human demonstrates PokeLLMon's human-like battle strategies and just-in-time decision making, achieving 49% of win rate in the Ladder competitions and 56% of win rate in the invited battles. Our implementation and playable battle logs are available at: https://github.com/git-disl/PokeLLMon.