We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs) with unobserved confounding. Recent advances have introduced bridge-function to circumvent unmeasured confounding and develop estimators for the policy value, yet the statistical error bounds of them related to the length of horizon $T$ and the size of the state-action space $|\mathcal{O}||\mathcal{A}|$ remain largely unexplored. In this paper, we systematically investigate the finite-sample error bounds of OPE estimators in finite-horizon tabular confounded POMDPs. Specifically, we show that under certain rank conditions, the estimation error for policy value can achieve a rate of $\mathcal{O}(T^{1.5}/\sqrt{n})$, excluding the cardinality of the observation space $|\mathcal{O}|$ and the action space $|\mathcal{A}|$. With an additional mild condition on the concentrability coefficients in confounded POMDPs, the rate of estimation error can be improved to $\mathcal{O}(T/\sqrt{n})$. We also show that for a fully history-dependent policy, the estimation error scales as $\mathcal{O}\big(T/\sqrt{n}(|\mathcal{O}| |\mathcal{A}|)^{\frac{T}{2}}\big)$, highlighting the exponential error dependence introduced by history-based proxies to infer hidden states. Furthermore, when the target policy is memoryless policy, the error bound improves to $\mathcal{O}\big(T/\sqrt{n}\sqrt{|\mathcal{O}| |\mathcal{A}|}\big)$, which matches the optimal rate known for tabular MDPs. To the best of our knowledge, this is the first work to provide a comprehensive finite-sample analysis of OPE in confounded POMDPs.

Although distributional reinforcement learning (DRL) has been widely examined in the past few years, very few studies investigate the validity of the obtained Q-function estimator in the distributional setting. To fully understand how the approximation errors of the Q-function affect the whole training process, we do some error analysis and theoretically show how to reduce both the bias and the variance of the error terms. With this new understanding, we construct a new estimator Quantiled Expansion Mean (QEM) and introduce a new DRL algorithm (QEMRL) from the statistical perspective. We extensively evaluate our QEMRL algorithm on a variety of Atari and Mujoco benchmark tasks and demonstrate that QEMRL achieves significant improvement over baseline algorithms in terms of sample efficiency and convergence performance.

Although distributional reinforcement learning (DRL) has been widely examined in the past few years, there are two open questions people are still trying to address. One is how to ensure the validity of the learned quantile function, the other is how to efficiently utilize the distribution information. This paper attempts to provide some new perspectives to encourage the future in-depth studies in these two fields. We first propose a non-decreasing quantile function network (NDQFN) to guarantee the monotonicity of the obtained quantile estimates and then design a general exploration framework called distributional prediction error (DPE) for DRL which utilizes the entire distribution of the quantile function. In this paper, we not only discuss the theoretical necessity of our method but also show the performance gain it achieves in practice by comparing with some competitors on Atari 2600 Games especially in some hard-explored games.

Unmanned aerial vehicles (UAVs) are frequently used for large-scale scene mapping and reconstruction. However, in most cases, drones are operated manually, which should be more effective and intelligent. In this article, we present a method of real-time UAV path planning for autonomous urban scene reconstruction. Considering the obstacles and time costs, we utilize the top view to generate the initial path. Then we estimate the building heights and take close-up pictures that reveal building details through a SLAM framework. To predict the coverage of the scene, we propose a novel method which combines information on reconstructed point clouds and possible coverage areas. The experimental results reveal that the reconstruction quality of our method is good enough. Our method is also more time-saving than the state-of-the-arts.

Despite the growing number of unmanned aerial vehicles (UAVs) and aerial videos, there is a paucity of studies focusing on the aesthetics of aerial videos that can provide valuable information for improving the aesthetic quality of aerial photography. In this article, we present a method of deep multimodality learning for UAV video aesthetic quality assessment. More specifically, a multistream framework is designed to exploit aesthetic attributes from multiple modalities, including spatial appearance, drone camera motion, and scene structure. A novel specially designed motion stream network is proposed for this new multistream framework. We construct a dataset with 6,000 UAV video shots captured by drone cameras. Our model can judge whether a UAV video was shot by professional photographers or amateurs together with the scene type classification. The experimental results reveal that our method outperforms the video classification methods and traditional SVM-based methods for video aesthetics. In addition, we present three application examples of UAV video grading, professional segment detection and aesthetic-based UAV path planning using the proposed method.