We consider the problem of local planning in fixed-horizon and discounted Markov Decision Processes (MDPs) with linear function approximation and a generative model under the assumption that the optimal action-value function lies in the span of a feature map that is available to the planner. Previous work has left open the question of whether there exist sound planners that need only poly(H,d) queries regardless of the MDP, where H is the horizon and d is the dimensionality of the features. We answer this question in the negative: we show that any sound planner must query at least $\min(\exp({\Omega}(d)), {\Omega}(2^H))$ samples in the fized-horizon setting and $\exp({\Omega}(d))$ samples in the discounted setting. We also show that for any ${\delta}>0$, the least-squares value iteration algorithm with $O(H^5d^{H+1}/{\delta}^2)$ queries can compute a ${\delta}$-optimal policy in the fixed-horizon setting. We discuss implications and remaining open questions.
翻译:我们考虑了固定正数和折扣的Markov 决策程序(MDPs)的本地规划问题,该程序具有线性功能近似值和基因模型,假设最佳行动价值功能存在于可供计划者使用的地貌图范围内。以前的工作没有解决一个问题,即是否存在只需要多(H,d)查询的健全的规划者,而不论MDP,H是地平线,d是特征的维度。我们否定地回答这个问题:我们显示,任何健全的规划者必须至少查询美元(exmo(femega}(d))) 、 emega}(2(2) ) 美元,在Fizd-horizon 设置和 $\ exp(@Omega} (d) ) 在折扣环境中是否只有多(H,d) 查询,而H是地平线和 d是特征的维度。我们还表明,对于任何$(delta)0美元,最差值的 Iteration 算法值为$(H5d_H+1}/ delta ⁇ 2) 查询中至少可以计算出$xelta$-homon-imp-imprizet polist-resplest polist poli-s imp impesution impesution impesution impetions。