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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Sihao, Huang, Tiansheng, Liu, Ling
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914738297896960
author Hu, Sihao
Huang, Tiansheng
Liu, Ling
author_facet Hu, Sihao
Huang, Tiansheng
Liu, Ling
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01118
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
Hu, Sihao
Huang, Tiansheng
Liu, Ling
Artificial Intelligence
Computation and Language
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.
title PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2402.01118