论文标题
最小描述长度控制
Minimum Description Length Control
论文作者
论文摘要
我们提出了一个基于最小描述长度（MDL）原理的多任务加固学习的新框架。在我们称MDL-Control（MDL-C）的这种方法中，代理商在面临的任务之间学习了共同的结构，然后将其提炼成更简单的表示，从而促进了更快的融合和对新任务的概括。这样一来，MDL-C自然将适应性适应与任务分布的认知不确定性平衡。我们通过MDL原理与贝叶斯推论之间的正式联系来激励MDL-C，得出理论性能保证，并在离散和高维连续控制任务上展示了MDL-C的经验有效性。
We propose a novel framework for multitask reinforcement learning based on the minimum description length (MDL) principle. In this approach, which we term MDL-control (MDL-C), the agent learns the common structure among the tasks with which it is faced and then distills it into a simpler representation which facilitates faster convergence and generalization to new tasks. In doing so, MDL-C naturally balances adaptation to each task with epistemic uncertainty about the task distribution. We motivate MDL-C via formal connections between the MDL principle and Bayesian inference, derive theoretical performance guarantees, and demonstrate MDL-C's empirical effectiveness on both discrete and high-dimensional continuous control tasks.
