This paper revisits the recently proposed reward centering algorithms including simple reward centering (SRC) and value-based reward centering (VRC), and points out that SRC is indeed the reward centering, while VRC is essentially Bellman error centering (BEC). Based on BEC, we provide the centered fixpoint for tabular value functions, as well as the centered TD fixpoint for linear value function approximation. We design the on-policy CTD algorithm and the off-policy CTDC algorithm, and prove the convergence of both algorithms. Finally, we experimentally validate the stability of our proposed algorithms. Bellman error centering facilitates the extension to various reinforcement learning algorithms.

Fast-converging algorithms are a contemporary requirement in reinforcement learning. In the context of linear function approximation, the magnitude of the smallest eigenvalue of the key matrix is a major factor reflecting the convergence speed. Traditional value-based RL algorithms focus on minimizing errors. This paper introduces a variance minimization (VM) approach for value-based RL instead of error minimization. Based on this approach, we proposed two objectives, the Variance of Bellman Error (VBE) and the Variance of Projected Bellman Error (VPBE), and derived the VMTD, VMTDC, and VMETD algorithms. We provided proofs of their convergence and optimal policy invariance of the variance minimization. Experimental studies validate the effectiveness of the proposed algorithms.

Model-based offline reinforcement learning (RL), which builds a supervised transition model with logging dataset to avoid costly interactions with the online environment, has been a promising approach for offline policy optimization. As the discrepancy between the logging data and online environment may result in a distributional shift problem, many prior works have studied how to build robust transition models conservatively and estimate the model uncertainty accurately. However, the over-conservatism can limit the exploration of the agent, and the uncertainty estimates may be unreliable. In this work, we propose a novel Model-based Offline policy optimization framework with Adversarial Network (MOAN). The key idea is to use adversarial learning to build a transition model with better generalization, where an adversary is introduced to distinguish between in-distribution and out-of-distribution samples. Moreover, the adversary can naturally provide a quantification of the model's uncertainty with theoretical guarantees. Extensive experiments showed that our approach outperforms existing state-of-the-art baselines on widely studied offline RL benchmarks. It can also generate diverse in-distribution samples, and quantify the uncertainty more accurately.

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks.

There are two classes of average reward reinforcement learning (RL) algorithms: model-based ones that explicitly maintain MDP models and model-free ones that do not learn such models. Though model-free algorithms are known to be more efficient, they often cannot converge to optimal policies due to the perturbation of parameters. In this paper, a novel model-free algorithm is proposed, which makes use of constant shifting values (CSVs) estimated from prior knowledge. To encourage exploration during the learning process, the algorithm constantly subtracts the CSV from the rewards. A terminating condition is proposed to handle the unboundedness of Q-values caused by such substraction. The convergence of the proposed algorithm is proved under very mild assumptions. Furthermore, linear function approximation is investigated to generalize our method to handle large-scale tasks. Extensive experiments on representative MDPs and the popular game Tetris show that the proposed algorithms significantly outperform the state-of-the-art ones.

With the rapid development of mobile devices, global position system (GPS) and Web 2.0 technologies, location-based social networks (LBSNs) have attracted millions of users to share rich information, such as experiences and tips. Point-of-Interest (POI) recommender system plays an important role in LBSNs since it can help users explore attractive locations as well as help social network service providers design location-aware advertisements for Point-of-Interest. In this paper, we present a brief survey over the task of Point-of-Interest recommendation in LBSNs and discuss some research directions for Point-of-Interest recommendation. We first describe the unique characteristics of Point-of-Interest recommendation, which distinguish Point-of-Interest recommendation approaches from traditional recommendation approaches. Then, according to what type of additional information are integrated with check-in data by POI recommendation algorithms, we classify POI recommendation algorithms into four categories: pure check-in data based POI recommendation approaches, geographical influence enhanced POI recommendation approaches, social influence enhanced POI recommendation approaches and temporal influence enhanced POI recommendation approaches. Finally, we discuss future research directions for Point-of-Interest recommendation.