{"ID":2846891,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.02094","arxiv_id":"2511.02094","title":"Automated Reward Design for Gran Turismo","abstract":"When designing reinforcement learning (RL) agents, a designer communicates the desired agent behavior through the definition of reward functions - numerical feedback given to the agent as reward or punishment for its actions. However, mapping desired behaviors to reward functions can be a difficult process, especially in complex environments such as autonomous racing. In this paper, we demonstrate how current foundation models can effectively search over a space of reward functions to produce desirable RL agents for the Gran Turismo 7 racing game, given only text-based instructions. Through a combination of LLM-based reward generation, VLM preference-based evaluation, and human feedback we demonstrate how our system can be used to produce racing agents competitive with GT Sophy, a champion-level RL racing agent, as well as generate novel behaviors, paving the way for practical automated reward design in real world applications.","short_abstract":"When designing reinforcement learning (RL) agents, a designer communicates the desired agent behavior through the definition of reward functions - numerical feedback given to the agent as reward or punishment for its actions. However, mapping desired behaviors to reward functions can be a difficult process, especially...","url_abs":"https://arxiv.org/abs/2511.02094","url_pdf":"https://arxiv.org/pdf/2511.02094v1","authors":"[\"Michel Ma\",\"Takuma Seno\",\"Kaushik Subramanian\",\"Peter R. Wurman\",\"Peter Stone\",\"Craig Sherstan\"]","published":"2025-11-03T22:07:53Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}