Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning perspective. Prior RMAB research suffers from several limitations, e.g., it fails to adequately address continuous states, and requires retraining from scratch when arms opt-in and opt-out over time, a common challenge in many real world applications. We address these limitations by developing a neural network-based pre-trained model (PreFeRMAB) that has general zero-shot ability on a wide range of previously unseen RMABs, and which can be fine-tuned on specific instances in a more sample-efficient way than retraining from scratch. Our model also accommodates general multi-action settings and discrete or continuous state spaces. To enable fast generalization, we learn a novel single policy network model that utilizes feature information and employs a training procedure in which arms opt-in and out over time. We derive a new update rule for a crucial $\lambda$-network with theoretical convergence guarantees and empirically demonstrate the advantages of our approach on several challenging, real-world inspired problems.

Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human annotation of hundreds of thousands of instructions. Thus, we propose SPRINT, a scalable offline policy pre-training approach which substantially reduces the human effort needed for pre-training a diverse set of skills. Our method uses two core ideas to automatically expand a base set of pre-training tasks: instruction relabeling via large language models and cross-trajectory skill chaining through offline reinforcement learning. As a result, SPRINT pre-training equips robots with a much richer repertoire of skills. Experimental results in a household simulator and on a real robot kitchen manipulation task show that SPRINT leads to substantially faster learning of new long-horizon tasks than previous pre-training approaches. Website at https://clvrai.com/sprint.

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational weakness: they require repeatedly solving a hard reinforcement learning (RL) problem as a subroutine. This is counter-intuitive from the viewpoint of reductions: we have reduced the easier problem of imitation learning to repeatedly solving the harder problem of RL. Another thread of work has proved that access to the side-information of the distribution of states where a strong policy spends time can dramatically reduce the sample and computational complexities of solving an RL problem. In this work, we demonstrate for the first time a more informed imitation learning reduction where we utilize the state distribution of the expert to alleviate the global exploration component of the RL subroutine, providing an exponential speedup in theory. In practice, we find that we are able to significantly speed up the prior art on continuous control tasks.

Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either do not consider the temporal aspect of the problem or only consider single-step transitions, which may cause learning inefficiencies if important environmental changes take many steps to manifest. We propose Hierarchical $k$-Step Latent (HKSL), an auxiliary task that learns multiple representations via a hierarchy of forward models that learn to communicate and an ensemble of $n$-step critics that all operate at varying magnitudes of step skipping. We evaluate HKSL in a suite of 30 robotic control tasks with and without distractors and a task of our creation. We find that HKSL either converges to higher or optimal episodic returns more quickly than several alternative representation learning approaches. Furthermore, we find that HKSL's representations capture task-relevant details accurately across timescales (even in the presence of distractors) and that communication channels between hierarchy levels organize information based on both sides of the communication process, both of which improve sample efficiency.

Sample efficiency is central to developing practical reinforcement learning (RL) for complex and large-scale decision-making problems. The ability to transfer and generalize knowledge gained from previous experiences to downstream tasks can significantly improve sample efficiency. Recent research indicates that successor feature (SF) RL algorithms enable knowledge generalization between tasks with different rewards but identical transition dynamics. It has recently been hypothesized that combining model-based (MB) methods with SF algorithms can alleviate the limitation of fixed transition dynamics. Furthermore, uncertainty-aware exploration is widely recognized as another appealing approach for improving sample efficiency. Putting together two ideas of hybrid model-based successor feature (MB-SF) and uncertainty leads to an approach to the problem of sample efficient uncertainty-aware knowledge transfer across tasks with different transition dynamics or/and reward functions. In this paper, the uncertainty of the value of each action is approximated by a Kalman filter (KF)-based multiple-model adaptive estimation. This KF-based framework treats the parameters of a model as random variables. To the best of our knowledge, this is the first attempt at formulating a hybrid MB-SF algorithm capable of generalizing knowledge across large or continuous state space tasks with various transition dynamics while requiring less computation at decision time than MB methods. The number of samples required to learn the tasks was compared to recent SF and MB baselines. The results show that our algorithm generalizes its knowledge across different transition dynamics, learns downstream tasks with significantly fewer samples than starting from scratch, and outperforms existing approaches.

Autonomous vehicles are suited for continuous area patrolling problems. Finding an optimal patrolling strategy can be challenging due to unknown environmental factors, such as wind or landscape; or autonomous vehicles' constraints, such as limited battery life or hardware failures. Importantly, patrolling large areas often requires multiple agents to collectively coordinate their actions. However, an optimal coordination strategy is often non-trivial to be manually defined due to the complex nature of patrolling environments. In this paper, we consider a patrolling problem with environmental factors, agent limitations, and three typical cooperation problems -- collision avoidance, congestion avoidance, and patrolling target negotiation. We propose a multi-agent reinforcement learning solution based on a reinforced inter-agent learning (RIAL) method. With this approach, agents are trained to develop their own communication protocol to cooperate during patrolling where faults can and do occur. The solution is validated through simulation experiments and is compared with several state-of-the-art patrolling solutions from different perspectives, including the overall patrol performance, the collision avoidance performance, the efficiency of battery recharging strategies, and the overall fault tolerance.

This study aims to minimize the influence of fake news on social networks by deploying debunkers to propagate true news. This is framed as a reinforcement learning problem, where, at each stage, one user is selected to propagate true news. A challenging issue is episodic reward where the "net" effect of selecting individual debunkers cannot be discerned from the interleaving information propagation on social networks, and only the collective effect from mitigation efforts can be observed. Existing Self-Imitation Learning (SIL) methods have shown promise in learning from episodic rewards, but are ill-suited to the real-world application of fake news mitigation because of their poor sample efficiency. To learn a more effective debunker selection policy for fake news mitigation, this study proposes NAGASIL - Negative sampling and state Augmented Generative Adversarial Self-Imitation Learning, which consists of two improvements geared towards fake news mitigation: learning from negative samples, and an augmented state representation to capture the "real" environment state by integrating the current observed state with the previous state-action pairs from the same campaign. Experiments on two social networks show that NAGASIL yields superior performance to standard GASIL and state-of-the-art fake news mitigation models.

Digital Twins (DT) have become crucial to achieve sustainable and effective smart urban solutions. However, current DT modelling techniques cannot support the dynamicity of these smart city environments. This is caused by the lack of right-time data capturing in traditional approaches, resulting in inaccurate modelling and high resource and energy consumption challenges. To fill this gap, we explore spatiotemporal graphs and propose the Reinforcement Learning-based Adaptive Twining (RL-AT) mechanism with Deep Q Networks (DQN). By doing so, our study contributes to advancing Green Cities and showcases tangible benefits in accuracy, synchronisation, resource optimization, and energy efficiency. As a result, we note the spatiotemporal graphs are able to offer a consistent accuracy and 55% higher querying performance when implemented using graph databases. In addition, our model demonstrates right-time data capturing with 20% lower overhead and 25% lower energy consumption.

This paper addresses a multi-echelon inventory management problem with a complex network topology where deriving optimal ordering decisions is difficult. Deep reinforcement learning (DRL) has recently shown potential in solving such problems, while designing the neural networks in DRL remains a challenge. In order to address this, a DRL model is developed whose Q-network is based on radial basis functions. The approach can be more easily constructed compared to classic DRL models based on neural networks, thus alleviating the computational burden of hyperparameter tuning. Through a series of simulation experiments, the superior performance of this approach is demonstrated compared to the simple base-stock policy, producing a better policy in the multi-echelon system and competitive performance in the serial system where the base-stock policy is optimal. In addition, the approach outperforms current DRL approaches.

Solutions to Markov Decision Processes (MDP) are often very sensitive to state transition probabilities. As the estimation of these probabilities is often inaccurate in practice, it is important to understand when and how Reinforcement Learning (RL) agents generalize when transition probabilities change. Here we present a new methodology to evaluate such generalization of RL agents under small shifts in the transition probabilities. Specifically, we evaluate agents in new environments (MDPs) in the vicinity of the training MDP created by adding quantifiable, parametric noise into the transition function of the training MDP. We refer to this process as Noise Injection, and the resulting environments as $\delta$-environments. This process allows us to create controlled variations of the same environment with the level of the noise serving as a metric of distance between environments. Conventional wisdom suggests that training and testing on the same MDP should yield the best results. However, we report several cases of the opposite -- when targeting a specific environment, training the agent in an alternative noise setting can yield superior outcomes. We showcase this phenomenon across $60$ different variations of ATARI games, including PacMan, Pong, and Breakout.