In settings where the application of reinforcement learning (RL) requires running real-world trials, including the optimization of adaptive health interventions, the number of episodes available for learning can be severely limited due to cost or time constraints. In this setting, the bias-variance trade-off of contextual bandit methods can be significantly better than that of more complex full RL methods. However, Thompson sampling bandits are limited to selecting actions based on distributions of immediate rewards. In this paper, we extend the linear Thompson sampling bandit to select actions based on a state-action utility function consisting of the Thompson sampler's estimate of the expected immediate reward combined with an action bias term. We use batch Bayesian optimization over episodes to learn the action bias terms with the goal of maximizing the expected return of the extended Thompson sampler. The proposed approach is able to learn optimal policies for a strictly broader class of Markov decision processes (MDPs) than standard Thompson sampling. Using an adaptive intervention simulation environment that captures key aspects of behavioral dynamics, we show that the proposed method can significantly out-perform standard Thompson sampling in terms of total return, while requiring significantly fewer episodes than standard value function and policy gradient methods.

This paper introduces SANGO (Socially Aware Navigation through Grouped Obstacles), a novel method that ensures socially appropriate behavior by dynamically grouping obstacles and adhering to social norms. Using deep reinforcement learning, SANGO trains agents to navigate complex environments leveraging the DBSCAN algorithm for obstacle clustering and Proximal Policy Optimization (PPO) for path planning. The proposed approach improves safety and social compliance by maintaining appropriate distances and reducing collision rates. Extensive experiments conducted in custom simulation environments demonstrate SANGO's superior performance in significantly reducing discomfort (by up to 83.5%), reducing collision rates (by up to 29.4%) and achieving higher successful navigation in dynamic and crowded scenarios. These findings highlight the potential of SANGO for real-world applications, paving the way for advanced socially adept robotic navigation systems.

In recent years, model-based reinforcement learning (MBRL) has emerged as a solution to address sample complexity in multi-agent reinforcement learning (MARL) by modeling agent-environment dynamics to improve sample efficiency. However, most MBRL methods assume complete and continuous observations from each agent during the inference stage, which can be overly idealistic in practical applications. A novel model-based MARL approach called RMIO is introduced to address this limitation, specifically designed for scenarios where observation is lost in some agent. RMIO leverages the world model to reconstruct missing observations, and further reduces reconstruction errors through inter-agent information integration to ensure stable multi-agent decision-making. Secondly, unlike CTCE methods such as MAMBA, RMIO adopts the CTDE paradigm in standard environment, and enabling limited communication only when agents lack observation data, thereby reducing reliance on communication. Additionally, RMIO improves asymptotic performance through strategies such as reward smoothing, a dual-layer experience replay buffer, and an RNN-augmented policy model, surpassing previous work. Our experiments conducted in both the SMAC and MaMuJoCo environments demonstrate that RMIO outperforms current state-of-the-art approaches in terms of asymptotic convergence performance and policy robustness, both in standard mission settings and in scenarios involving observation loss.

Due to climate change the frequency and intensity of extreme rainfall events, which contribute to urban flooding, are expected to increase in many places. These floods can damage transport infrastructure and disrupt mobility, highlighting the need for cities to adapt to escalating risks. Reinforcement learning (RL) serves as a powerful tool for uncovering optimal adaptation strategies, determining how and where to deploy adaptation measures effectively, even under significant uncertainty. In this study, we leverage RL to identify the most effective timing and locations for implementing measures, aiming to reduce both direct and indirect impacts of flooding. Our framework integrates climate change projections of future rainfall events and floods, models city-wide motorized trips, and quantifies direct and indirect impacts on infrastructure and mobility. Preliminary results suggest that our RL-based approach can significantly enhance decision-making by prioritizing interventions in specific urban areas and identifying the optimal periods for their implementation. Our framework is publicly available: https://github.com/

In this paper, we explore how to optimize task allocation for robot swarms in dynamic environments, emphasizing the necessity of formulating robust, flexible, and scalable strategies for robot cooperation. We introduce a novel framework using a decentralized partially observable Markov decision process (Dec_POMDP), specifically designed for distributed robot swarm networks. At the core of our methodology is the Local Information Aggregation Multi-Agent Deep Deterministic Policy Gradient (LIA_MADDPG) algorithm, which merges centralized training with distributed execution (CTDE). During the centralized training phase, a local information aggregation (LIA) module is meticulously designed to gather critical data from neighboring robots, enhancing decision-making efficiency. In the distributed execution phase, a strategy improvement method is proposed to dynamically adjust task allocation based on changing and partially observable environmental conditions. Our empirical evaluations show that the LIA module can be seamlessly integrated into various CTDE-based MARL methods, significantly enhancing their performance. Additionally, by comparing LIA_MADDPG with six conventional reinforcement learning algorithms and a heuristic algorithm, we demonstrate its superior scalability, rapid adaptation to environmental changes, and ability to maintain both stability and convergence speed. These results underscore LIA_MADDPG's outstanding performance and its potential to significantly improve dynamic task allocation in robot swarms through enhanced local collaboration and adaptive strategy execution.

This paper studies reinforcement learning (RL) in infinite-horizon dynamic decision processes with almost-sure safety constraints. Such safety-constrained decision processes are central to applications in autonomous systems, finance, and resource management, where policies must satisfy strict, state-dependent constraints. We consider a doubly-regularized RL framework that combines reward and parameter regularization to address these constraints within continuous state-action spaces. Specifically, we formulate the problem as a convex regularized objective with parametrized policies in the mean-field regime. Our approach leverages recent developments in mean-field theory and Wasserstein gradient flows to model policies as elements of an infinite-dimensional statistical manifold, with policy updates evolving via gradient flows on the space of parameter distributions. Our main contributions include establishing solvability conditions for safety-constrained problems, defining smooth and bounded approximations that facilitate gradient flows, and demonstrating exponential convergence towards global solutions under sufficient regularization. We provide general conditions on regularization functions, encompassing standard entropy regularization as a special case. The results also enable a particle method implementation for practical RL applications. The theoretical insights and convergence guarantees presented here offer a robust framework for safe RL in complex, high-dimensional decision-making problems.

This study integrates Transit Signal Priority (TSP) into multi-agent reinforcement learning (MARL) based traffic signal control. The first part of the study develops adaptive signal control based on MARL for a pair of coordinated intersections in a microscopic simulation environment. The two agents, one for each intersection, are centrally trained using a value decomposition network (VDN) architecture. The trained agents show slightly better performance compared to coordinated actuated signal control based on overall intersection delay at v/c of 0.95. In the second part of the study the trained signal control agents are used as background signal controllers while developing event-based TSP agents. In one variation, independent TSP agents are formulated and trained under a decentralized training and decentralized execution (DTDE) framework to implement TSP at each intersection. In the second variation, the two TSP agents are centrally trained under a centralized training and decentralized execution (CTDE) framework and VDN architecture to select and implement coordinated TSP strategies across the two intersections. In both cases the agents converge to the same bus delay value, but independent agents show high instability throughout the training process. For the test runs, the two independent agents reduce bus delay across the two intersections by 22% compared to the no TSP case while the coordinated TSP agents achieve 27% delay reduction. In both cases, there is only a slight increase in delay for a majority of the side street movements.

Link adaptation (LA) is an essential function in modern wireless communication systems that dynamically adjusts the transmission rate of a communication link to match time- and frequency-varying radio link conditions. However, factors such as user mobility, fast fading, imperfect channel quality information, and aging of measurements make the modeling of LA challenging. To bypass the need for explicit modeling, recent research has introduced online reinforcement learning (RL) approaches as an alternative to the more commonly used rule-based algorithms. Yet, RL-based approaches face deployment challenges, as training in live networks can potentially degrade real-time performance. To address this challenge, this paper considers offline RL as a candidate to learn LA policies with minimal effects on the network operation. We propose three LA designs based on batch-constrained deep Q-learning, conservative Q-learning, and decision transformer. Our results show that offline RL algorithms can match the performance of state-of-the-art online RL methods when data is collected with a proper behavioral policy.

Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must identify and address the sources of this variance. Recent research on Concept Bottleneck Models (CBMs) shows that using human-explainable concepts can improve predictions and provide better understanding. We propose incorporating concepts into OPE to reduce variance. Our work introduces a family of concept-based OPE estimators, proving that they remain unbiased and reduce variance when concepts are known and predefined. Since real-world applications often lack predefined concepts, we further develop an end-to-end algorithm to learn interpretable, concise, and diverse parameterized concepts optimized for variance reduction. Our experiments with synthetic and real-world datasets show that both known and learned concept-based estimators significantly improve OPE performance. Crucially, we show that, unlike other OPE methods, concept-based estimators are easily interpretable and allow for targeted interventions on specific concepts, further enhancing the quality of these estimators.

Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as "zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present \emph{Proto Successor Measure}: the basis set for all possible solutions of Reinforcement Learning in a dynamical system. We provably show that any possible policy can be represented using an affine combination of these policy independent basis functions. Given a reward function at test time, we simply need to find the right set of linear weights to combine these basis corresponding to the optimal policy. We derive a practical algorithm to learn these basis functions using only interaction data from the environment and show that our approach can produce the optimal policy at test time for any given reward function without additional environmental interactions. Project page: https://agarwalsiddhant10.github.io/projects/psm.html.