{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pokellmon-a-human-parity-agent-for-pokemon","title":"PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models","arxiv_id":"2402.01118","date":"2024-02-02","proceeding":null,"authors":["Sihao Hu","Tiansheng Huang","Ling Liu"],"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.","url_abs":"https://arxiv.org/abs/2402.01118v3","url_pdf":"https://arxiv.org/pdf/2402.01118v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pokellmon-a-human-parity-agent-for-pokemon","repo_url":"https://github.com/git-disl/pokellmon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":null,"task_name":"In-Context Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.01118","atlas_url":"https://app.syntology.ai/?focus=2402.01118","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}