arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.05912cs.AI
收藏

强化学习中奖励机与策略的联合推理

Joint Inference of Reward Machines and Policies for Reinforcement Learning

Oden Institute for Computational Engineering and Sciences, University of Texas, Austin(得克萨斯大学奥斯汀分校奥登计算工程与科学研究所);Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所)

Zhe Xu, Ivan Gavran, Yousef Ahmad, Rupak Majumdar, Daniel Neider, Ufuk Topcu, Bo Wu

摘要:

高级知识的提取是加速强化学习(RL)的有效方法,特别是对于具有稀疏奖励的复杂任务。我们研究了一个强化学习问题,其中高级知识是奖励机器的形式,即,一种编码奖励函数的Mealy机器。我们专注于一个设置中,这种知识是先验的学习代理不可用。我们开发了一种迭代算法,可以对RL(更具体地说,q学习)的奖励机和策略进行联合推理。在每次迭代中,该算法维护一个假设奖励机和RL事件的样本。它从当前的假设奖励机导出q函数,并执行RL来更新q函数。在执行RL时,该算法通过添加RL情节来更新样本,沿着RL情节获得的奖励与基于当前假设奖励机的奖励不一致。在下一次迭代中,该算法从更新的样本中推断出新的假设奖励机。基于我们定义的等价关系的状态之间的奖励机,我们转移的q-函数之间的假设奖励机在连续的迭代。我们证明了,该算法几乎肯定收敛到一个最优的政策,如果一个最小的奖励机器可以推断,每个RL情节的最大长度是足够长的限制。实验表明,以奖励机器的形式学习高级知识可以导致RL快速收敛到最优策略,而标准RL方法(如q学习和分层RL方法)在许多任务中经过大量训练步骤后无法收敛到最优策略。

英文摘要:

Incorporating high-level knowledge is an effective way to expedite reinforcement learning (RL), especially for complex tasks with sparse rewards. We investigate an RL problem where the high-level knowledge is in the form of reward machines, i.e., a type of Mealy machine that encodes the reward functions. We focus on a setting in which this knowledge is a priori not available to the learning agent. We develop an iterative algorithm that performs joint inference of reward machines and policies for RL (more specifically, q-learning). In each iteration, the algorithm maintains a hypothesis reward machine and a sample of RL episodes. It derives q-functions from the current hypothesis reward machine, and performs RL to update the q-functions. While performing RL, the algorithm updates the sample by adding RL episodes along which the obtained rewards are inconsistent with the rewards based on the current hypothesis reward machine. In the next iteration, the algorithm infers a new hypothesis reward machine from the updated sample. Based on an equivalence relationship we defined between states of reward machines, we transfer the q-functions between the hypothesis reward machines in consecutive iterations. We prove that the proposed algorithm converges almost surely to an optimal policy in the limit if a minimal reward machine can be inferred and the maximal length of each RL episode is sufficiently long. The experiments show that learning high-level knowledge in the form of reward machines can lead to fast convergence to optimal policies in RL, while standard RL methods such as q-learning and hierarchical RL methods fail to converge to optimal policies after a substantial number of training steps in many tasks.

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。

↑