arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1405.3229cs.LGcs.AImath.OCmath.STstat.TH
收藏

LSTD($λ$)的收敛速度和误差界

Rate of Convergence and Error Bounds for LSTD($λ$)

INRIA Nancy Grand Est(法国国家信息与自动化研究所南锡大东部大区中心)

Manel Tagorti, Bruno Scherrer

摘要:

我们考虑LSTD($λ$),Boyan(2002)提出的最小二乘时间差分算法和合格迹算法。它计算大型马尔可夫决策过程中固定策略的价值函数的线性近似。根据$β$混合假设,我们推导出,对于任何值的$λ\in (0,1)$,高概率估计的速度收敛到其极限。我们推导出该算法误差的高概率界,该界扩展(并略微改进)了Lazaric等人(2012)在$λ=0$ .特别是,我们的分析揭示了一些光的选择$λ$相对于所选择的线性空间的质量和样本的数量,符合模拟。

英文摘要:

We consider LSTD($λ$), the least-squares temporal-difference algorithm with eligibility traces algorithm proposed by Boyan (2002). It computes a linear approximation of the value function of a fixed policy in a large Markov Decision Process. Under a $β$-mixing assumption, we derive, for any value of $λ\in (0,1)$, a high-probability estimate of the rate of convergence of this algorithm to its limit. We deduce a high-probability bound on the error of this algorithm, that extends (and slightly improves) that derived by Lazaric et al. (2012) in the specific case where $λ=0$. In particular, our analysis sheds some light on the choice of $λ$ with respect to the quality of the chosen linear space and the number of samples, that complies with simulations.

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。

↑