Communication at terahertz (THz) frequency bands is a promising solution for achieving extremely high data rates in next-generation wireless networks. While the THz communication is conventionally envisioned for short-range wireless applications due to the high atmospheric absorption at THz frequencies, multi-hop directional transmissions can be enabled to extend the communication range. However, to realize multi-hop THz communications, conventional beam training schemes, such as exhaustive search or hierarchical methods with a fixed number of training levels, can lead to a very large time overhead. To address this challenge, in this paper, a novel hierarchical beam training scheme with dynamic training levels is proposed to optimize the performance of multi-hop THz links. In fact, an optimization problem is formulated to maximize the overall spectral efficiency of the multi-hop THz link by dynamically and jointly selecting the number of beam training levels across all the constituent single-hop links. To solve this problem in presence of unknown channel state information, noise, and path loss, a new reinforcement learning solution based on the multi-armed bandit (MAB) is developed. Simulation results show the fast convergence of the proposed scheme in presence of random channels and noise. The results also show that the proposed scheme can yield up to 75% performance gain, in terms of spectral efficiency, compared to the conventional hierarchical beam training with a fixed number of training levels.

Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time. To avoid time-discretization approximation of the underlying process, we propose a continuous-time MBRL framework based on a novel actor-critic method. Our approach also infers the unknown state evolution differentials with Bayesian neural ordinary differential equations (ODE) to account for epistemic uncertainty. We implement and test our method on a new ODE-RL suite that explicitly solves continuous-time control systems. Our experiments illustrate that the model is robust against irregular and noisy data, is sample-efficient, and can solve control problems which pose challenges to discrete-time MBRL methods.

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research area, known as offline RL, has largely focused on offline policy optimization, aiming to find a return-maximizing policy exclusively from offline data. In this paper, we consider a slightly different approach to incorporating offline data into sequential decision-making. We aim to answer the question, what unsupervised objectives applied to offline datasets are able to learn state representations which elevate performance on downstream tasks, whether those downstream tasks be online RL, imitation learning from expert demonstrations, or even offline policy optimization based on the same offline dataset? Through a variety of experiments utilizing standard offline RL datasets, we find that the use of pretraining with unsupervised learning objectives can dramatically improve the performance of policy learning algorithms that otherwise yield mediocre performance on their own. Extensive ablations further provide insights into what components of these unsupervised objectives -- e.g., reward prediction, continuous or discrete representations, pretraining or finetuning -- are most important and in which settings.

We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards, with the optimality gap specified by an attack parameter. Our goal is to design agents that are robust against such attacks in terms of the worst-case utility w.r.t. the true, unpoisoned, rewards while computing their policies under the poisoned rewards. We propose an optimization framework for deriving optimal defense policies, both when the attack parameter is known and unknown. Moreover, we show that defense policies that are solutions to the proposed optimization problems have provable performance guarantees. In particular, we provide the following bounds with respect to the true, unpoisoned, rewards: a) lower bounds on the expected return of the defense policies, and b) upper bounds on how suboptimal these defense policies are compared to the attacker's target policy. We conclude the paper by illustrating the intuitions behind our formal results, and showing that the derived bounds are non-trivial.

In this work, we address risk-averse Bayesadaptive reinforcement learning. We pose the problem of optimising the conditional value at risk (CVaR) of the total return in Bayes-adaptive Markov decision processes (MDPs). We show that a policy optimising CVaR in this setting is risk-averse to both the parametric uncertainty due to the prior distribution over MDPs, and the internal uncertainty due to the inherent stochasticity of MDPs. We reformulate the problem as a two-player stochastic game and propose an approximate algorithm based on Monte Carlo tree search and Bayesian optimisation. Our experiments demonstrate that our approach significantly outperforms baseline approaches for this problem.

Despite the recent success of deep reinforcement learning (RL), domain adaptation remains an open problem. Although the generalization ability of RL agents is critical for the real-world applicability of Deep RL, zero-shot policy transfer is still a challenging problem since even minor visual changes could make the trained agent completely fail in the new task. To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on LUSR in the second stage. The cross-domain consistency of LUSR allows the policy acquired from the source domain to generalize to other target domains without extra training. We first demonstrate our approach in variants of CarRacing games with customized manipulations, and then verify it in CARLA, an autonomous driving simulator with more complex and realistic visual observations. Our results show that this approach can achieve state-of-the-art domain adaptation performance in related RL tasks and outperforms prior approaches based on latent-representation based RL and image-to-image translation.

Reinforcement learning is about learning agent models that make the best sequential decisions in unknown environments. In an unknown environment, the agent needs to explore the environment while exploiting the collected information, which usually forms a sophisticated problem to solve. Derivative-free optimization, meanwhile, is capable of solving sophisticated problems. It commonly uses a sampling-and-updating framework to iteratively improve the solution, where exploration and exploitation are also needed to be well balanced. Therefore, derivative-free optimization deals with a similar core issue as reinforcement learning, and has been introduced in reinforcement learning approaches, under the names of learning classifier systems and neuroevolution/evolutionary reinforcement learning. Although such methods have been developed for decades, recently, derivative-free reinforcement learning exhibits attracting increasing attention. However, recent survey on this topic is still lacking. In this article, we summarize methods of derivative-free reinforcement learning to date, and organize the methods in aspects including parameter updating, model selection, exploration, and parallel/distributed methods. Moreover, we discuss some current limitations and possible future directions, hoping that this article could bring more attentions to this topic and serve as a catalyst for developing novel and efficient approaches.

With astonishing speed, bandwidth, and scale, Mobile Edge Computing (MEC) has played an increasingly important role in the next generation of connectivity and service delivery. Yet, along with the massive deployment of MEC servers, the ensuing energy issue is now on an increasingly urgent agenda. In the current context, the large scale deployment of renewable-energy-supplied MEC servers is perhaps the most promising solution for the incoming energy issue. Nonetheless, as a result of the intermittent nature of their power sources, these special design MEC server must be more cautious about their energy usage, in a bid to maintain their service sustainability as well as service standard. Targeting optimization on a single-server MEC scenario, we in this paper propose NAFA, an adaptive processor frequency adjustment solution, to enable an effective plan of the server's energy usage. By learning from the historical data revealing request arrival and energy harvest pattern, the deep reinforcement learning-based solution is capable of making intelligent schedules on the server's processor frequency, so as to strike a good balance between service sustainability and service quality. The superior performance of NAFA is substantiated by real-data-based experiments, wherein NAFA demonstrates up to 20% increase in average request acceptance ratio and up to 50% reduction in average request processing time.

We propose a black-box reduction that turns a certain reinforcement learning algorithm with optimal regret in a (near-)stationary environment into another algorithm with optimal dynamic regret in a non-stationary environment, importantly without any prior knowledge on the degree of non-stationarity. By plugging different algorithms into our black-box, we provide a list of examples showing that our approach not only recovers recent results for (contextual) multi-armed bandits achieved by very specialized algorithms, but also significantly improves the state of the art for linear bandits, episodic MDPs, and infinite-horizon MDPs in various ways. Specifically, in most cases our algorithm achieves the optimal dynamic regret $\widetilde{\mathcal{O}}(\min\{\sqrt{LT}, \Delta^{1/3}T^{2/3}\})$ where $T$ is the number of rounds and $L$ and $\Delta$ are the number and amount of changes of the world respectively, while previous works only obtain suboptimal bounds and/or require the knowledge of $L$ and $\Delta$.

Deep reinforcement learning has made significant progress in the last few years, with success stories in robotic control, game playing and science problems. While RL methods present a general paradigm where an agent learns from its own interaction with an environment, this requirement for "active" data collection is also a major hindrance in the application of RL methods to real-world problems, since active data collection is often expensive and potentially unsafe. An alternative "data-driven" paradigm of RL, referred to as offline RL (or batch RL) has recently regained popularity as a viable path towards effective real-world RL. As shown in the figure below, offline RL requires learning skills solely from previously collected datasets, without any active environment interaction. It provides a way to utilize previously collected datasets from a variety of sources, including human demonstrations, prior experiments, domain-specific solutions and even data from different but related problems, to build complex decision-making engines.