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 2102.05261cs.LGcs.AI
收藏

简单Agent,复杂环境:基于Agent状态的高效强化学习

Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States

Stanford University(斯坦福大学);New York University(纽约大学)

Shi Dong, Benjamin Van Roy, Zhengyuan Zhou

摘要:

我们设计了一个简单的强化学习(RL)代理,实现了一个乐观的版本的$Q$ -学习,并建立通过后悔分析,这个代理可以在任何环境中的某种程度的能力。虽然我们利用文献中可证明有效的RL的概念,我们考虑了一个通用的代理环境接口,并提供了一个新的代理设计和分析。这种水平的一般性定位我们的研究结果,以告知未来的代理在复杂的现实环境中操作的设计。我们确定,随着时间的推移,我们的代理执行相对于政策,需要更长的时间来评估的竞争力。接近渐近性能所需的时间是多项式的代理的状态表示的复杂性和评估代理可以表示的最佳策略所需的时间。值得注意的是,它不依赖于环境的复杂性。代理的最终每周期性能损失由代理的状态表示所引入的失真的度量的常数倍来限定。这项工作是第一次建立一个算法在一个易于处理的时间框架内接近这个渐近条件。

英文摘要:

We design a simple reinforcement learning (RL) agent that implements an optimistic version of $Q$-learning and establish through regret analysis that this agent can operate with some level of competence in any environment. While we leverage concepts from the literature on provably efficient RL, we consider a general agent-environment interface and provide a novel agent design and analysis. This level of generality positions our results to inform the design of future agents for operation in complex real environments. We establish that, as time progresses, our agent performs competitively relative to policies that require longer times to evaluate. The time it takes to approach asymptotic performance is polynomial in the complexity of the agent's state representation and the time required to evaluate the best policy that the agent can represent. Notably, there is no dependence on the complexity of the environment. The ultimate per-period performance loss of the agent is bounded by a constant multiple of a measure of distortion introduced by the agent's state representation. This work is the first to establish that an algorithm approaches this asymptotic condition within a tractable time frame.

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。

↑