Learning Game-Playing Agents with Generative Code Optimization
By: Zhiyi Kuang , Ryan Rong , YuCheng Yuan and more
Potential Business Impact:
Teaches computers to play games by writing code.
We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving code, with current observation as input and an in-game action as output, enabling agents to self-improve through execution traces and natural language feedback with minimal human intervention. Applied to Atari games, our game-playing Python program achieves performance competitive with deep reinforcement learning (RL) baselines while using significantly less training time and much fewer environment interactions. This work highlights the promise of programmatic policy representations for building efficient, adaptable agents capable of complex, long-horizon reasoning.
Similar Papers
Design and Optimization of Reinforcement Learning-Based Agents in Text-Based Games
Computation and Language
AI learns to win text games better.
Agent-based code generation for the Gammapy framework
Software Engineering
Helps scientists write computer code for research.
GoRL: An Algorithm-Agnostic Framework for Online Reinforcement Learning with Generative Policies
Machine Learning (CS)
Lets robots learn complex moves safely and quickly.