Attention-based sequential recommendation methods have demonstrated promising results by accurately capturing users' dynamic interests from historical interactions. In addition to generating superior user representations, recent studies have begun integrating reinforcement learning (RL) into these models. Framing sequential recommendation as an RL problem with reward signals, unlocks developing recommender systems (RS) that consider a vital aspect-incorporating direct user feedback in the form of rewards to deliver a more personalized experience. Nonetheless, employing RL algorithms presents challenges, including off-policy training, expansive combinatorial action spaces, and the scarcity of datasets with sufficient reward signals. Contemporary approaches have attempted to combine RL and sequential modeling, incorporating contrastive-based objectives and negative sampling strategies for training the RL component. In this study, we further emphasize the efficacy of contrastive-based objectives paired with augmentation to address datasets with extended horizons. Additionally, we recognize the potential instability issues that may arise during the application of negative sampling. These challenges primarily stem from the data imbalance prevalent in real-world datasets, which is a common issue in offline RL contexts. While our established baselines attempt to mitigate this through various techniques, instability remains an issue. Therefore, we introduce an enhanced methodology aimed at providing a more effective solution to these challenges.

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings. We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo, an efficient type of Markov Chain Monte Carlo (MCMC) method. Our method only needs to perform noisy gradient descent updates to learn the exact posterior distribution of the Q function, which makes our approach easy to deploy in deep RL. We provide a rigorous theoretical analysis for the proposed method and demonstrate that, in the linear Markov decision process (linear MDP) setting, it has a regret bound of $\tilde{O}(d^{3/2}H^{5/2}\sqrt{T})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $T$ is the total number of steps. We apply this approach to deep RL, by using Adam optimizer to perform gradient updates. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.

Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most RL methods operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that these methods are limited in their ability to fully leverage the privileged knowledge, resulting in suboptimal performance. In this paper, we propose a novel single-stage privileged knowledge distillation method called the Historical Information Bottleneck (HIB) to narrow the sim-to-real gap. In particular, HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Theoretical analysis shows that the learned privileged knowledge representation helps reduce the value discrepancy between the oracle and learned policies. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods.

The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL). However, LTL has the downside that it is sensitive to small perturbations in the transition probabilities, which prevents probably approximately correct (PAC) learning without additional assumptions. Time discounting provides a way of removing this sensitivity, while retaining the high expressivity of the logic. We study the use of discounted LTL for policy synthesis in Markov decision processes with unknown transition probabilities, and show how to reduce discounted LTL to discounted-sum reward via a reward machine when all discount factors are identical.

Multi-step learning applies lookahead over multiple time steps and has proved valuable in policy evaluation settings. However, in the optimal control case, the impact of multi-step learning has been relatively limited despite a number of prior efforts. Fundamentally, this might be because multi-step policy improvements require operations that cannot be approximated by stochastic samples, hence hindering the widespread adoption of such methods in practice. To address such limitations, we introduce doubly multi-step off-policy VI (DoMo-VI), a novel oracle algorithm that combines multi-step policy improvements and policy evaluations. DoMo-VI enjoys guaranteed convergence speed-up to the optimal policy and is applicable in general off-policy learning settings. We then propose doubly multi-step off-policy actor-critic (DoMo-AC), a practical instantiation of the DoMo-VI algorithm. DoMo-AC introduces a bias-variance trade-off that ensures improved policy gradient estimates. When combined with the IMPALA architecture, DoMo-AC has showed improvements over the baseline algorithm on Atari-57 game benchmarks.

Rapid developments in artificial intelligence technology have led to unmanned systems replacing human beings in many fields requiring high-precision predictions and decisions. In modern operational environments, all job plans are affected by emergency events such as equipment failures and resource shortages, making a quick resolution critical. The use of unmanned systems to assist decision-making can improve resolution efficiency, but their decision-making is not interpretable and may make the wrong decisions. Current unmanned systems require human supervision and control. Based on this, we propose a collaborative human--machine method for resolving unplanned events using two phases: task filtering and task scheduling. In the task filtering phase, we propose a human--machine collaborative decision-making algorithm for dynamic tasks. The GACRNN model is used to predict the state of the job nodes, locate the key nodes, and generate a machine-predicted resolution task list. A human decision-maker supervises the list in real time and modifies and confirms the machine-predicted list through the human--machine interface. In the task scheduling phase, we propose a scheduling algorithm that integrates human experience constraints. The steps to resolve an event are inserted into the normal job sequence to schedule the resolution. We propose several human--machine collaboration methods in each phase to generate steps to resolve an unplanned event while minimizing the impact on the original job plan.

In reinforcement learning, the advantage function is critical for policy improvement, but is often extracted from a learned Q-function. A natural question is: Why not learn the advantage function directly? In this work, we introduce VA-learning, which directly learns advantage function and value function using bootstrapping, without explicit reference to Q-functions. VA-learning learns off-policy and enjoys similar theoretical guarantees as Q-learning. Thanks to the direct learning of advantage function and value function, VA-learning improves the sample efficiency over Q-learning both in tabular implementations and deep RL agents on Atari-57 games. We also identify a close connection between VA-learning and the dueling architecture, which partially explains why a simple architectural change to DQN agents tends to improve performance.

Is it possible to evaluate the moral cognition of complex artificial agents? In this work, we take a look at one aspect of morality: `doing the right thing for the right reasons.' We propose a behavior-based analysis of artificial moral cognition which could also be applied to humans to facilitate like-for-like comparison. Morally-motivated behavior should persist despite mounting cost; by measuring an agent's sensitivity to this cost, we gain deeper insight into underlying motivations. We apply this evaluation to a particular set of deep reinforcement learning agents, trained by memory-based meta-reinforcement learning. Our results indicate that agents trained with a reward function that includes other-regarding preferences perform helping behavior in a way that is less sensitive to increasing cost than agents trained with more self-interested preferences.

Risk-sensitive reinforcement learning (RL) has become a popular tool to control the risk of uncertain outcomes and ensure reliable performance in various sequential decision-making problems. While policy gradient methods have been developed for risk-sensitive RL, it remains unclear if these methods enjoy the same global convergence guarantees as in the risk-neutral case. In this paper, we consider a class of dynamic time-consistent risk measures, called Expected Conditional Risk Measures (ECRMs), and derive policy gradient updates for ECRM-based objective functions. Under both constrained direct parameterization and unconstrained softmax parameterization, we provide global convergence and iteration complexities of the corresponding risk-averse policy gradient algorithms. We further test risk-averse variants of REINFORCE and actor-critic algorithms to demonstrate the efficacy of our method and the importance of risk control.

In this paper, we develop a hierarchical aerial computing framework composed of high altitude platform (HAP) and unmanned aerial vehicles (UAVs) to compute the fully offloaded tasks of terrestrial mobile users which are connected through an uplink non-orthogonal multiple access (UL-NOMA). To better assess the freshness of information in computation-intensive applications the criterion of age of information (AoI) is considered. In particular, the problem is formulated to minimize the average AoI of users with elastic tasks, by adjusting UAVs trajectory and resource allocation on both UAVs and HAP, which is restricted by the channel state information (CSI) uncertainty and multiple resource constraints of UAVs and HAP. In order to solve this non-convex optimization problem, two methods of multi-agent deep deterministic policy gradient (MADDPG) and federated reinforcement learning (FRL) are proposed to design the UAVs trajectory, and obtain channel, power, and CPU allocations. It is shown that task scheduling significantly reduces the average AoI. This improvement is more pronounced for larger task sizes. On one hand, it is shown that power allocation has a marginal effect on the average AoI compared to using full transmission power for all users. Compared with traditional transmission schemes, the simulation results show our scheduling scheme results in a substantial improvement in average AoI.