PokeRL: Reinforcement Learning for Pokemon Red

• URL: http://arxiv.org/abs/2604.10812v1
• Date: Sun, 12 Apr 2026 20:46:47 GMT
• Title: PokeRL: Reinforcement Learning for Pokemon Red
• Abstract summary: We present PokeRL, a modular system that trains deep reinforcement learning agents to complete early game tasks in Pokemon Red.<n>Our main contributions are a loop-aware environment wrapper around the PyBoy emulator with map masking, a multi-layer anti-loop and anti-spam mechanism, and a dense hierarchical reward design.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pokemon Red is a long-horizon JRPG with sparse rewards, partial observability, and quirky control mechanics that make it a challenging benchmark for reinforcement learning. While recent work has shown that PPO agents can clear the first two gyms using heavy reward shaping and engineered observations, training remains brittle in practice, with agents often degenerating into action loops, menu spam, or unproductive wandering. In this paper, we present PokeRL, a modular system that trains deep reinforcement learning agents to complete early game tasks in Pokemon Red, including exiting the player's house, exploring Pallet Town to reach tall grass, and winning the first rival battle. Our main contributions are a loop-aware environment wrapper around the PyBoy emulator with map masking, a multi-layer anti-loop and anti-spam mechanism, and a dense hierarchical reward design. We argue that practical systems like PokeRL, which explicitly model failure modes such as loops and spam, are a necessary intermediate step between toy benchmarks and full Pokemon League champion agents. Code is available at https://github.com/reddheeraj/PokemonRL

Related papers

• PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search [51.56484100374058]
  We revisit Tesauro's TDGammon for backgammon money games in the setting of no evaluation-time search.<n>Both checker play and cube action are learned from scratch via self-play reinforcement learning (RL), with minimal hand-coded logic and no expert features.
  arXiv  Detail & Related papers  (2026-08-15T09:46:03Z)
• The PokeAgent Challenge: Competitive and Long-Context Learning at Scale [45.224407977351824]
  PokeAgent Challenge is a large-scale benchmark for decisionmaking research.<n>It is built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environment.<n>Our NeurIPS 2025 competition validates both the quality of our resources and the research community's interest in Pokemon.
  arXiv  Detail & Related papers  (2026-03-16T17:25:42Z)
• Large Language Models as Pokémon Battle Agents: Strategic Play and Content Generation [4.782714372521615]
  Pokémon battles demand reasoning about type matchups, statistical trade-offs, and risk assessment.<n>This work examines whether Large Language Models (LLMs) can serve as competent battle agents.<n>We developed a turn-based Pokémon battle system where LLMs select moves based on battle state rather than pre-programmed logic.
  arXiv  Detail & Related papers  (2025-12-19T07:46:29Z)
• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning [89.93384726755106]
  Vision-language reinforcement learning (RL) has primarily focused on narrow domains.<n>We find video games inherently provide rich visual elements and mechanics that are easy to verify.<n>To fully use the multimodal and verifiable reward in video games, we propose Game-RL.
  arXiv  Detail & Related papers  (2025-05-20T03:47:44Z)
• Pokemon Red via Reinforcement Learning [3.548348926427221]
  Pok'emon Red, a classic Game Boy JRPG, presents significant challenges as a testbed for agents.<n>We introduce a simplistic environment and a Deep Reinforcement Learning training methodology, demonstrating a baseline agent that completes an initial segment of the game up to completing Cerulean City.<n>Our experiments include various ablations that reveal vulnerabilities in reward shaping, where agents exploit specific reward signals.
  arXiv  Detail & Related papers  (2025-02-27T09:42:23Z)
• PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models [7.653580388741887]
  We introduce PokeLLMon, the first LLM-embodied agent that achieves human-parity performance in tactical battle games. We show that online battles against human demonstrates PokeLLMon's human-like battle strategies and just-in-time decision making.
  arXiv  Detail & Related papers  (2024-02-02T03:22:12Z)
• Configurable Agent With Reward As Input: A Play-Style Continuum Generation [0.0]
  We present a video game environment which lets us define multiple play-styles. We then introduce CARI: a Reinforcement Learning agent able to simulate a wide range of play-styles.
  arXiv  Detail & Related papers  (2022-11-29T13:59:25Z)
• GridToPix: Training Embodied Agents with Minimal Supervision [87.05256520152723]
  GridToPix trains agents with terminal rewards in gridworlds that mirror Embodied AI environments. Despite learning from only terminal rewards with identical models and RL algorithms, GridToPix significantly improves results across tasks.
  arXiv  Detail & Related papers  (2021-04-14T17:59:57Z)
• DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games [137.86426963572214]
  We introduce DeepCrawl, a fully-playable Roguelike prototype for iOS and Android in which all agents are controlled by policy networks trained using Deep Reinforcement Learning (DRL) Our aim is to understand whether recent advances in DRL can be used to develop convincing behavioral models for non-player characters in videogames.
  arXiv  Detail & Related papers  (2020-12-03T13:53:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.