Traditionally, Reinforcement Learning (RL) problems are aimed at optimization of the behavior of an agent. This paper proposes a novel take on RL, which is used to learn the policy of another agent, to allow real-time recognition of that agent's goals. Goal Recognition (GR) has traditionally been framed as a planning problem where one must recognize an agent's objectives based on its observed actions. Recent approaches have shown how reinforcement learning can be used as part of the GR pipeline, but are limited to recognizing predefined goals and lack scalability in domains with a large goal space. This paper formulates a novel problem, "Online Dynamic Goal Recognition" (ODGR), as a first step to address these limitations. Contributions include introducing the concept of dynamic goals into the standard GR problem definition, revisiting common approaches by reformulating them using ODGR, and demonstrating the feasibility of solving ODGR in a navigation domain using transfer learning. These novel formulations open the door for future extensions of existing transfer learning-based GR methods, which will be robust to changing and expansive real-time environments.

Supporting real-time interactions between human controllers and remote devices remains a challenging goal in the Metaverse due to the stringent requirements on computing workload, communication throughput, and round-trip latency. In this paper, we establish a novel framework for real-time interactions through the virtual models in the Metaverse. Specifically, we jointly predict the motion of the human controller for 1) proactive rendering in the Metaverse and 2) generating control commands to the real-world remote device in advance. The virtual model is decoupled into two components for rendering and control, respectively. To dynamically adjust the prediction horizons for rendering and control, we develop a two-step human-in-the-loop continuous reinforcement learning approach and use an expert policy to improve the training efficiency. An experimental prototype is built to verify our algorithm with different communication latencies. Compared with the baseline policy without prediction, our proposed method can reduce 1) the Motion-To-Photon (MTP) latency between human motion and rendering feedback and 2) the root mean squared error (RMSE) between human motion and real-world remote devices significantly.

Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitating progress, evaluation, and reproducibility. The significance of benchmarks is underscored by the existence of numerous benchmark frameworks developed for various RL paradigms, including single-agent RL (e.g., Gymnasium), multi-agent RL (e.g., PettingZoo), and single-agent multi-objective RL (e.g., MO-Gymnasium). To support the advancement of the MOMARL field, we introduce MOMAland, the first collection of standardised environments for multi-objective multi-agent reinforcement learning. MOMAland addresses the need for comprehensive benchmarking in this emerging field, offering over 10 diverse environments that vary in the number of agents, state representations, reward structures, and utility considerations. To provide strong baselines for future research, MOMAland also includes algorithms capable of learning policies in such settings.

Many roboticists dream of presenting a robot with a task in the evening and returning the next morning to find the robot capable of solving the task. What is preventing us from achieving this? Sim-to-real reinforcement learning (RL) has achieved impressive performance on challenging robotics tasks, but requires substantial human effort to set up the task in a way that is amenable to RL. It's our position that algorithmic improvements in policy optimization and other ideas should be guided towards resolving the primary bottleneck of shaping the training environment, i.e., designing observations, actions, rewards and simulation dynamics. Most practitioners don't tune the RL algorithm, but other environment parameters to obtain a desirable controller. We posit that scaling RL to diverse robotic tasks will only be achieved if the community focuses on automating environment shaping procedures.

Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused on learning domain translation, they often struggle with handling significant domain gaps or out-of-distribution tasks. In this paper, we present a simple approach for cross-domain policy transfer that learns a shared latent representation across domains and a common abstract policy on top of it. Our approach leverages multi-domain behavioral cloning on unaligned trajectories of proxy tasks and employs maximum mean discrepancy (MMD) as a regularization term to encourage cross-domain alignment. The MMD regularization better preserves structures of latent state distributions than commonly used domain-discriminative distribution matching, leading to higher transfer performance. Moreover, our approach involves training only one multi-domain policy, which makes extension easier than existing methods. Empirical evaluations demonstrate the efficacy of our method across various domain shifts, especially in scenarios where exact domain translation is challenging, such as cross-morphology or cross-viewpoint settings. Our ablation studies further reveal that multi-domain behavioral cloning implicitly contributes to representation alignment alongside domain-adversarial regularization. Humans have an astonishing ability to learn skills in a highly transferable way. Once we learn a route from home to the station, for example, we can get to the destination using various modes of transportation (e.g., walking, cycling, or driving) in different environments (e.g., on a map or in the real world), disregarding irrelevant perturbations (e.g., weather, time, or traffic conditions). We identify the underlying structural similarities across situations, perceive the world, and accumulate knowledge in our way of abstraction. Such abstract knowledge can be readily employed in diverse similar situations. However, it is not easy for autonomous agents. Agents trained with reinforcement learning (RL) or imitation learning (IL) often struggle to transfer knowledge acquired in a specific situation to another. This is because the learned policies are strongly tied to the representations obtained under a particular training configuration, which is not robust to changes in an agent or an environment. Previous studies have attempted to address this problem through various approaches. Domain randomization (Tobin et al., 2017; Peng et al., 2018; Andrychowicz et al., 2020) aims to learn a policy that is robust to environmental changes by utilizing multiple training domains. However, it is unable to handle significant domain gaps that go beyond the assumed domain distribution during training, such as drastically different observations or agent morphologies. Numerous methods have been proposed to overcome such domain discrepancies.

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward engineering and reward shaping in enhancing the efficiency and effectiveness of reinforcement learning algorithms. Reward engineering involves designing reward functions that accurately reflect the desired outcomes, while reward shaping provides additional feedback to guide the learning process, accelerating convergence to optimal policies. Despite significant advancements in reinforcement learning, several limitations persist. One key challenge is the sparse and delayed nature of rewards in many real-world scenarios, which can hinder learning progress. Additionally, the complexity of accurately modeling real-world environments and the computational demands of reinforcement learning algorithms remain substantial obstacles. On the other hand, recent advancements in deep learning and neural networks have significantly improved the capability of reinforcement learning systems to handle high-dimensional state and action spaces, enabling their application to complex tasks such as robotics, autonomous driving, and game playing. This paper provides a comprehensive review of the current state of reinforcement learning, focusing on the methodologies and techniques used in reward engineering and reward shaping. It critically analyzes the limitations and recent advancements in the field, offering insights into future research directions and potential applications in various domains.

Precision health, increasingly supported by digital technologies, is a domain of research that broadens the paradigm of precision medicine, advancing everyday healthcare. This vision goes hand in hand with the groundbreaking advent of artificial intelligence (AI), which is reshaping the way we diagnose, treat, and monitor both clinical subjects and the general population. AI tools powered by machine learning have shown considerable improvements in a variety of healthcare domains. In particular, reinforcement learning (RL) holds great promise for sequential and dynamic problems such as dynamic treatment regimes and just-in-time adaptive interventions in digital health. In this work, we discuss the opportunity offered by AI, more specifically RL, to current trends in healthcare, providing a methodological survey of RL methods in the context of precision and digital health. Focusing on the area of adaptive interventions, we expand the methodological survey with illustrative case studies that used RL in real practice. This invited article has undergone anonymous review and is intended as a book chapter for the volume "Frontiers of Statistics and Data Science" edited by Subhashis Ghoshal and Anindya Roy for the International Indian Statistical Association Series on Statistics and Data Science, published by Springer. It covers the material from a short course titled "Artificial Intelligence in Precision and Digital Health" taught by the author Bibhas Chakraborty at the IISA 2022 Conference, December 26-30 2022, at the Indian Institute of Science, Bengaluru.

To alleviate energy shortages and environmental impacts caused by transportation, this study introduces EcoFollower, a novel eco-car-following model developed using reinforcement learning (RL) to optimize fuel consumption in car-following scenarios. Employing the NGSIM datasets, the performance of EcoFollower was assessed in comparison with the well-established Intelligent Driver Model (IDM). The findings demonstrate that EcoFollower excels in simulating realistic driving behaviors, maintaining smooth vehicle operations, and closely matching the ground truth metrics of time-to-collision (TTC), headway, and comfort. Notably, the model achieved a significant reduction in fuel consumption, lowering it by 10.42\% compared to actual driving scenarios. These results underscore the capability of RL-based models like EcoFollower to enhance autonomous vehicle algorithms, promoting safer and more energy-efficient driving strategies.

To enhance therapeutic outcomes from a pharmacological perspective, we propose MiranDa, designed for medication recommendation, which is the first actionable model capable of providing the estimated length of stay in hospitals (ELOS) as counterfactual outcomes that guide clinical practice and model training. In detail, MiranDa emulates the educational trajectory of doctors through two gradient-scaling phases shifted by ELOS: an Evidence-based Training Phase that utilizes supervised learning and a Therapeutic Optimization Phase grounds in reinforcement learning within the gradient space, explores optimal medications by perturbations from ELOS. Evaluation of the Medical Information Mart for Intensive Care III dataset and IV dataset, showcased the superior results of our model across five metrics, particularly in reducing the ELOS. Surprisingly, our model provides structural attributes of medication combinations proved in hyperbolic space and advocated "procedure-specific" medication combinations. These findings posit that MiranDa enhanced medication efficacy. Notably, our paradigm can be applied to nearly all medical tasks and those with information to evaluate predicted outcomes. The source code of the MiranDa model is available at https://github.com/azusakou/MiranDa.

We consider the situation when a learner faces a set of unknown discrete distributions $(p_k)_{k\in \mathcal K}$ defined over a common alphabet $\mathcal X$, and can build for each distribution $p_k$ an individual high-probability confidence set thanks to $n_k$ observations sampled from $p_k$. The set $(p_k)_{k\in \mathcal K}$ is structured: each distribution $p_k$ is obtained from the same common, but unknown, distribution q via applying an unknown permutation to $\mathcal X$. We call this \emph{permutation-equivalence}. The goal is to build refined confidence sets \emph{exploiting} this structural property. Like other popular notions of structure (Lipschitz smoothness, Linearity, etc.) permutation-equivalence naturally appears in machine learning problems, and to benefit from its potential gain calls for a specific approach. We present a strategy to effectively exploit permutation-equivalence, and provide a finite-time high-probability bound on the size of the refined confidence sets output by the strategy. Since a refinement is not possible for too few observations in general, under mild technical assumptions, our finite-time analysis establish when the number of observations $(n_k)_{k\in \mathcal K}$ are large enough so that the output confidence sets improve over initial individual sets. We carefully characterize this event and the corresponding improvement. Further, our result implies that the size of confidence sets shrink at asymptotic rates of $O(1/\sqrt{\sum_{k\in \mathcal K} n_k})$ and $O(1/\max_{k\in K} n_{k})$, respectively for elements inside and outside the support of q, when the size of each individual confidence set shrinks at respective rates of $O(1/\sqrt{n_k})$ and $O(1/n_k)$. We illustrate the practical benefit of exploiting permutation equivalence on a reinforcement learning task.