Abstract:Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling robots using large language models (LLMs). In the content generation literature, there has been early work on generating reward functions for reinforcement learning agent generators. This work introduces PCGRLLM, an extended architecture based on earlier work, which employs a feedback mechanism and several reasoning-based prompt engineering techniques. We evaluate the proposed method on a story-to-reward generation task in a two-dimensional environment using two state-of-the-art LLMs across various reasoning-based prompting methods. Our experiments provide insightful evaluations that demonstrate the capabilities of LLMs essential for content generation tasks. The results demonstrate a substantial performance improvement over the previous structure, achieving performance comparable to that of humans. Our work demonstrates the potential to reduce human dependency in game AI development, while supporting and enhancing creative processes.
| Comments: | 14 pages, 8 figures, Acccepted to Transactions on Games |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2502.10906 [cs.AI] |
| (or arXiv:2502.10906v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2502.10906 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1109/TG.2026.3695197
DOI(s) linking to related resources |
From: In-Chang Baek [view email]
[v1]
Sat, 15 Feb 2025 21:00:40 UTC (6,890 KB)
[v2]
Mon, 25 May 2026 05:27:35 UTC (3,310 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。