arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.04004cs.LG
收藏

ACERAC:精细时间离散化中的高效强化学习

ACERAC: Efficient reinforcement learning in fine time discretization

Warsaw University of Technology(华沙理工大学)

Jakub Łyskawa, Paweł Wawrzyński

摘要:

强化学习(RL)的主要目标之一是为物理机器提供一种学习最佳行为的方法,而不是被编程。然而,机器的有效控制通常需要精细的时间离散化。最常见的RL方法对每个动作应用独立的随机元素,这不适合该设置。这是不可行的,因为它会导致受控系统的颠簸,并不能确保充分的探索,因为一个单一的行动是不够长的,以创造一个重要的经验,可以转化为政策的改善。在我们看来,这些是阻碍RL在当代控制系统中应用的主要障碍。为了解决这些问题,在本文中,我们引入了一个RL框架和足够的分析工具,用于在随后的时间实例中可能依赖于随机性的操作。我们还介绍了一个RL算法,近似优化的~政策,产生这样的行动。该方法应用经验重放来调整先前动作序列的似然性,以优化期望的$n$ -步回报,从而获得策略收益。该算法的效率进行了验证,对其他四个RL方法(CDAU,PPO,SAC,ACER)在四个模拟学习控制问题(蚂蚁,HalfCheetah,Hopper和Walker 2D)在不同的时间离散化。在大多数情况下,这里介绍的算法优于竞争对手。

英文摘要:

One of the main goals of reinforcement learning (RL) is to provide a~way for physical machines to learn optimal behavior instead of being programmed. However, effective control of the machines usually requires fine time discretization. The most common RL methods apply independent random elements to each action, which is not suitable in that setting. It is not feasible because it causes the controlled system to jerk, and does not ensure sufficient exploration since a~single action is not long enough to create a~significant experience that could be translated into policy improvement. In our view these are the main obstacles that prevent application of RL in contemporary control systems. To address these pitfalls, in this paper we introduce an RL framework and adequate analytical tools for actions that may be stochastically dependent in subsequent time instances. We also introduce an RL algorithm that approximately optimizes a~policy that produces such actions. It applies experience replay to adjust likelihood of sequences of previous actions to optimize expected $n$-step returns the policy yields. The efficiency of this algorithm is verified against four other RL methods (CDAU, PPO, SAC, ACER) in four simulated learning control problems (Ant, HalfCheetah, Hopper, and Walker2D) in diverse time discretization. The algorithm introduced here outperforms the competitors in most cases considered.

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。

↑