直接优势估计：可扩展且样本高效的深度强化学习
Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning
AI总结：
针对直接优势估计（DAE）在部分可观测域和高维观测下的局限性，本文扩展其理论框架并引入离散潜动态模型降低计算复杂度，在Arcade学习环境中验证了DAE的可扩展性和样本效率。
摘要：
直接优势估计（DAE）已被证明可以提高深度强化学习算法的样本效率。然而，它对完全环境可观测性的依赖限制了其在现实场景中的适用性，并且其对转移概率建模的要求在高维观测下会带来巨大的计算开销。在本文中，我们解决了这两个局限性。首先，我们将DAE的理论框架扩展到部分可观测域，只需最小的修改。其次，我们通过引入高效近似转移概率的离散潜动态模型来降低其计算复杂度。我们在Arcade学习环境上评估了我们的方法，发现DAE在保持高样本效率的同时，能有效地随函数逼近器容量扩展。
英文摘要：
Direct Advantage Estimation (DAE) has been shown to improve the sample efficiency of deep reinforcement learning algorithms. However, its reliance on full environment observability limits its applicability in realistic settings, and its requirement to model transition probabilities incurs substantial computational overhead for high-dimensional observations. In the present work, we address both limitations. First, we extend the theoretical framework of DAE to partially observable domains with minimal modifications. Second, we reduce its computational complexity by introducing discrete latent dynamics models that efficiently approximate transition probabilities. We evaluate our approach on the Arcade Learning Environment and find that DAE scales effectively with function approximator capacity while retaining high sample efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
