让游戏智能体自动设定目标收益，无需人工干预。
Target Return Optimizer for Multi-Game Decision Transformer
- 从离线数据中自动提取奖励信息，确定每款游戏的目标收益
- 在Atari游戏上提升多种策略性能，且无需额外训练
- 适合缺乏游戏先验知识的场景，推动自主智能体发展
实现跨多种游戏和任务具备鲁棒泛化能力的自主智能体，仍是人工智能研究的终极目标之一。基于Transformer的离线强化学习方法，如MultiGame Decision Transformer [Lee et al., 2022]，已在多种游戏或任务中表现出色。然而，这些方法高度依赖人类经验，在缺乏特定游戏知识的场景下难以实际部署。本文提出多游戏目标收益优化器（MTRO），在MultiGame Decision Transformer框架内，仅使用离线数据自动确定每款游戏的目标收益。MTRO通过从离线数据中提取环境奖励信息，自动化目标收益配置过程，无需额外训练，可无缝集成至现有架构。在Atari游戏上的实验表明，MTRO显著提升了多种强化学习策略的性能，展现出推动自主智能体发展的潜力。
原文摘要 · Abstract (English)
Achieving autonomous agents with robust generalization capabilities across diverse games and tasks remains one of the ultimate goals in AI research. Recent advancements in transformer-based offline reinforcement learning, exemplified by the MultiGame Decision Transformer [Lee et al., 2022], have shown remarkable performance across various games or tasks. However, these approaches depend heavily on human expertise, presenting substantial challenges for practical deployment, particularly in scenarios with limited prior game-specific knowledge. In this paper, we propose an algorithm called Multi-Game Target Return Optimizer (MTRO) to autonomously determine game-specific target returns within the Multi-Game Decision Transformer framework using solely offline datasets. MTRO addresses the existing limitations by automating the target return configuration process, leveraging environmental reward information extracted from offline datasets. Notably, MTRO does not require additional training, enabling seamless integration into existing Multi-Game Decision Transformer architectures. Our experimental evaluations on Atari games demonstrate that MTRO enhances the performance of RL policies across a wide array of games, underscoring its potential to advance the field of autonomous agent development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。