基于稀疏核表示的组合学习
Composable Learning with Sparse Kernel Representations
摘要：
提出了一种在再生核Hilbert空间中学习稀疏非参数控制器的强化学习算法。我们通过一个归一化的优势函数（NAF）的状态-动作函数的结构，提高了这种方法的样本复杂度。策略的这种表示能够有效地组合多个学习模型，而无需额外的训练样本或与环境的交互。我们证明了该算法的性能，学习避障政策，在多个模拟的机器人配备了激光扫描仪，同时在2D环境中导航。我们将组合操作应用于各种策略组合，并对其进行测试，以表明组合策略保留了其组件的性能。我们还将组合策略直接转移到在具有障碍物的竞技场中操作的物理平台，以展示一定程度的泛化。
英文摘要：
We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function (NAF). This representation of the policy enables efficiently composing multiple learned models without additional training samples or interaction with the environment. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment. We apply the composition operation to various policy combinations and test them to show that the composed policies retain the performance of their components. We also transfer the composed policy directly to a physical platform operating in an arena with obstacles in order to demonstrate a degree of generalization.
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。
