RL智能体在简化任务上表现骤降，暴露其依赖捷径的局限性。
Deep Reinforcement Learning Agents are not even close to Human Intelligence
- 通过简化游戏任务测试智能体泛化能力
- 智能体在更简单任务上性能大幅下降
- 适合关注AI泛化与真实智能的研究者
深度强化学习（RL）智能体在多种任务中表现出色，但缺乏零样本适应能力。现有鲁棒性评估多关注任务复杂化，而人类在复杂任务中也难以保持性能；然而，任务简化方面的评估尚未开展。为此，我们提出了HackAtari，一套基于街机学习环境（Arcade Learning Environments）的任务变体。实验表明，与人类相反，RL智能体在训练任务的简化版本上系统性出现严重性能下降，揭示了其对捷径的持续依赖。跨多种算法与架构的分析显示，RL智能体与人类行为智能之间存在显著差距，凸显了需要新基准和方法，强制进行超越静态评估协议的系统性泛化测试。仅在相同环境中训练与测试，不足以获得类人智能的智能体。
原文摘要 · Abstract (English)
Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations focus on tasks complexifications, for which human also struggle to maintain performances, no evaluation has been performed on tasks simplifications. To tackle this issue, we introduce HackAtari, a set of task variations of the Arcade Learning Environments. We use it to demonstrate that, contrary to humans, RL agents systematically exhibit huge performance drops on simpler versions of their training tasks, uncovering agents' consistent reliance on shortcuts. Our analysis across multiple algorithms and architectures highlights the persistent gap between RL agents and human behavioral intelligence, underscoring the need for new benchmarks and methodologies that enforce systematic generalization testing beyond static evaluation protocols. Training and testing in the same environment is not enough to obtain agents equipped with human-like intelligence.
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。