Police patrol units need to split their time between performing preventive patrol and being dispatched to serve emergency incidents. In the existing literature, patrol and dispatch decisions are often studied separately. We consider joint optimization of these two decisions to improve police operations efficiency and reduce response time to emergency calls. Methodology/results: We propose a novel method for jointly optimizing multi-agent patrol and dispatch to learn policies yielding rapid response times. Our method treats each patroller as an independent Q-learner (agent) with a shared deep Q-network that represents the state-action values. The dispatching decisions are chosen using mixed-integer programming and value function approximation from combinatorial action spaces. We demonstrate that this heterogeneous multi-agent reinforcement learning approach is capable of learning joint policies that outperform those optimized for patrol or dispatch alone. Managerial Implications: Policies jointly optimized for patrol and dispatch can lead to more effective service while targeting demonstrably flexible objectives, such as those encouraging efficiency and equity in response.

Lexicographic multi-objective problems, which impose a lexicographic importance order over the objectives, arise in many real-life scenarios. Existing Reinforcement Learning work directly addressing lexicographic tasks has been scarce. The few proposed approaches were all noted to be heuristics without theoretical guarantees as the Bellman equation is not applicable to them. Additionally, the practical applicability of these prior approaches also suffers from various issues such as not being able to reach the goal state. While some of these issues have been known before, in this work we investigate further shortcomings, and propose fixes for improving practical performance in many cases. We also present a policy optimization approach using our Lexicographic Projection Optimization (LPO) algorithm that has the potential to address these theoretical and practical concerns. Finally, we demonstrate our proposed algorithms on benchmark problems.

The development of satellite constellation applications is rapidly advancing due to increasing user demands, reduced operational costs, and technological advancements. However, a significant gap in the existing literature concerns reconfiguration and retasking issues within satellite constellations, which is the primary focus of our research. In this work, we critically assess the impact of satellite failures on constellation performance and the associated task requirements. To facilitate this analysis, we introduce a system modeling approach for GPS satellite constellations, enabling an investigation into performance dynamics and task distribution strategies, particularly in scenarios where satellite failures occur during mission-critical operations. Additionally, we introduce reinforcement learning (RL) techniques, specifically Q-learning, Policy Gradient, Deep Q-Network (DQN), and Proximal Policy Optimization (PPO), for managing satellite constellations, addressing the challenges posed by reconfiguration and retasking following satellite failures. Our results demonstrate that DQN and PPO achieve effective outcomes in terms of average rewards, task completion rates, and response times.

Off-road navigation on vertically challenging terrain, involving steep slopes and rugged boulders, presents significant challenges for wheeled robots both at the planning level to achieve smooth collision-free trajectories and at the control level to avoid rolling over or getting stuck. Considering the complex model of wheel-terrain interactions, we develop an end-to-end Reinforcement Learning (RL) system for an autonomous vehicle to learn wheeled mobility through simulated trial-and-error experiences. Using a custom-designed simulator built on the Chrono multi-physics engine, our approach leverages Proximal Policy Optimization (PPO) and a terrain difficulty curriculum to refine a policy based on a reward function to encourage progress towards the goal and penalize excessive roll and pitch angles, which circumvents the need of complex and expensive kinodynamic modeling, planning, and control. Additionally, we present experimental results in the simulator and deploy our approach on a physical Verti-4-Wheeler (V4W) platform, demonstrating that RL can equip conventional wheeled robots with previously unrealized potential of navigating vertically challenging terrain.

Goal-driven mobile robot navigation in map-less environments requires effective state representations for reliable decision-making. Inspired by the favorable properties of Bird's-Eye View (BEV) in point clouds for visual perception, this paper introduces a novel navigation approach named BEVNav. It employs deep reinforcement learning to learn BEV representations and enhance decision-making reliability. First, we propose a self-supervised spatial-temporal contrastive learning approach to learn BEV representations. Spatially, two randomly augmented views from a point cloud predict each other, enhancing spatial features. Temporally, we combine the current observation with consecutive frames' actions to predict future features, establishing the relationship between observation transitions and actions to capture temporal cues. Then, incorporating this spatial-temporal contrastive learning in the Soft Actor-Critic reinforcement learning framework, our BEVNav offers a superior navigation policy. Extensive experiments demonstrate BEVNav's robustness in environments with dense pedestrians, outperforming state-of-the-art methods across multiple benchmarks. \rev{The code will be made publicly available at https://github.com/LanrenzzzZ/BEVNav.

Dental disease is a prevalent chronic condition associated with substantial financial burden, personal suffering, and increased risk of systemic diseases. Despite widespread recommendations for twice-daily tooth brushing, adherence to recommended oral self-care behaviors remains sub-optimal due to factors such as forgetfulness and disengagement. To address this, we developed Oralytics, a mHealth intervention system designed to complement clinician-delivered preventative care for marginalized individuals at risk for dental disease. Oralytics incorporates an online reinforcement learning algorithm to determine optimal times to deliver intervention prompts that encourage oral self-care behaviors. We have deployed Oralytics in a registered clinical trial. The deployment required careful design to manage challenges specific to the clinical trials setting in the U.S. In this paper, we (1) highlight key design decisions of the RL algorithm that address these challenges and (2) conduct a re-sampling analysis to evaluate algorithm design decisions. A second phase (randomized control trial) of Oralytics is planned to start in spring 2025.

Safe reinforcement learning (SafeRL) extends standard reinforcement learning with the idea of safety, where safety is typically defined through the constraint of the expected cost return of a trajectory being below a set limit. However, this metric fails to distinguish how costs accrue, treating infrequent severe cost events as equal to frequent mild ones, which can lead to riskier behaviors and result in unsafe exploration. We introduce a new metric, expected maximum consecutive cost steps (EMCC), which addresses safety during training by assessing the severity of unsafe steps based on their consecutive occurrence. This metric is particularly effective for distinguishing between prolonged and occasional safety violations. We apply EMMC in both on- and off-policy algorithm for benchmarking their safe exploration capability. Finally, we validate our metric through a set of benchmarks and propose a new lightweight benchmark task, which allows fast evaluation for algorithm design.

Our research investigates the challenges Deep Reinforcement Learning (DRL) faces in complex, Partially Observable Markov Decision Processes (POMDP) such as autonomous driving (AD), and proposes a solution for vision-based navigation in these environments. Partial observability reduces RL performance significantly, and this can be mitigated by augmenting sensor information and data fusion to reflect a more Markovian environment. However, this necessitates an increasingly complex perception module, whose training via RL is complicated due to inherent limitations. As the neural network architecture becomes more complex, the reward function's effectiveness as an error signal diminishes since the only source of supervision is the reward, which is often noisy, sparse, and delayed. Task-irrelevant elements in images, such as the sky or certain objects, pose additional complexities. Our research adopts an offline-trained encoder to leverage large video datasets through self-supervised learning to learn generalizable representations. Then, we train a head network on top of these representations through DRL to learn to control an ego vehicle in the CARLA AD simulator. This study presents a broad investigation of the impact of different learning schemes for offline-training of encoders on the performance of DRL agents in challenging AD tasks. Furthermore, we show that the features learned by watching BDD100K driving videos can be directly transferred to achieve lane following and collision avoidance in CARLA simulator, in a zero-shot learning fashion. Finally, we explore the impact of various architectural decisions for the RL networks to utilize the transferred representations efficiently. Therefore, in this work, we introduce and validate an optimal way for obtaining suitable representations of the environment, and transferring them to RL networks.

Two issues of algorithmic collusion are addressed in this paper. First, we show that in a general class of symmetric games, including Prisoner's Dilemma, Bertrand competition, and any (nonlinear) mixture of first and second price auction, only (strict) Nash Equilibrium (NE) is stochastically stable. Therefore, the tacit collusion is driven by failure to learn NE due to insufficient learning, instead of learning some strategies to sustain collusive outcomes. Second, we study how algorithms adapt to collusion in real simulations with insufficient learning. Extensive explorations in early stages and discount factors inflates the Q-value, which interrupts the sequential and alternative price undercut and leads to bilateral rebound. The process is iterated, making the price curves like Edgeworth cycles. When both exploration rate and Q-value decrease, algorithms may bilaterally rebound to relatively high common price level by coincidence, and then get stuck. Finally, we accommodate our reasoning to simulation outcomes in the literature, including optimistic initialization, market design and algorithm design.

Bugs in popular distributed protocol implementations have been the source of many downtimes in popular internet services. We describe a randomized testing approach for distributed protocol implementations based on reinforcement learning. Since the natural reward structure is very sparse, the key to successful exploration in reinforcement learning is reward augmentation. We show two different techniques that build on one another. First, we provide a decaying exploration bonus based on the discovery of new states -- the reward decays as the same state is visited multiple times. The exploration bonus captures the intuition from coverage-guided fuzzing of prioritizing new coverage points; in contrast to other schemes, we show that taking the maximum of the bonus and the Q-value leads to more effective exploration. Second, we provide waypoints to the algorithm as a sequence of predicates that capture interesting semantic scenarios. Waypoints exploit designer insight about the protocol and guide the exploration to ``interesting'' parts of the state space. Our reward structure ensures that new episodes can reliably get to deep interesting states even without execution caching. We have implemented our algorithm in Go. Our evaluation on three large benchmarks (RedisRaft, Etcd, and RSL) shows that our algorithm can significantly outperform baseline approaches in terms of coverage and bug finding.