Reinforcement learning (RL) can transform power grid operations by providing adaptive and scalable controllers essential for grid decarbonization. However, existing methods struggle with the complex dynamics, aleatoric uncertainty, long-horizon goals, and hard physical constraints that occur in real-world systems. This paper presents RL2Grid, a benchmark designed in collaboration with power system operators to accelerate progress in grid control and foster RL maturity. Built on a power simulation framework developed by RTE France, RL2Grid standardizes tasks, state and action spaces, and reward structures within a unified interface for a systematic evaluation and comparison of RL approaches. Moreover, we integrate real control heuristics and safety constraints informed by the operators' expertise to ensure RL2Grid aligns with grid operation requirements. We benchmark popular RL baselines on the grid control tasks represented within RL2Grid, establishing reference performance metrics. Our results and discussion highlight the challenges that power grids pose for RL methods, emphasizing the need for novel algorithms capable of handling real-world physical systems.

Furthermore, when evaluating the performance on 600 operations FJSP (10, 20, 30) in Table 1, we see that option (1) and (2), results in a longer solve time but an improved makespan from the architecture without attention. We also note that option (3) is strictly dominated by the performance of the architecture without attention. We note that the TNR-TPR tradeoff on the performance and solve time aligns with our theoretical analysis, as fixing something that should not have been (low TNR) harms the objective but helps the solve time, while failing to fix something that should have been (low TPR) harms the solve time and also indirectly harms the objective (under a fixed time limit). Due to the time benefit of the architecture without attention and the relatively competitive objective, we believe it makes sense to keep the simpler architecture without attention in the main paper.Figure 7: Ablation neural architecture: Attention among the overlapping and new operations. The architecture follows Figure 1, but introduces an additional cross attention among the overlapping and new operations before output the predicted probability for each overlapping operation.

This significant contribution makes it a critical sector for climate change mitigation, as reducing emissions from transportation is essential for achieving global climate goals. The sector's transformation through electrification, automation, and intelligent infrastructure offers promising avenues for substantial emissions reductions (Sciarretta et al., 2020; International Energy Agency, 2023; McKinsey Center for Future Mobility, 2023). However, the success of these innovations is critically dependent on the availability of suitable and accurate emission estimation models to guide the design and deployment of new technologies. Motor Vehicle Emission Simulation (MOVES) (U.S. Environmental Protection Agency, 2022), one of the most well-established emission estimation models, serves as the official and state-of-the-art emission estimation model in the U.S., provided, enforced, and maintained by the U.S. Environmental Protection Agency (EPA). Despite its technical certification, MOVES' processing and software is tailored for two specific governmental uses: State Implementation Plans and Conformity Analyses U.S. Environmental Protection Agency (2021), which are for states to achieve and maintain air quality standards; and its use beyond trained practitioners and these specific analyses poses two main limitations. First, a steep learning curve, computational demands, and complex inputs make it difficult for researchers and practitioners to use. In particular, MOVES has rigid input requirements, including a combination of toggle-based settings within its GUI and structured input files in specific formats. Second, MOVES is tailored for macroscopic analysis and is unsuitable for microscopic applications, such as control and optimization, which commonly require second-by-second emission calculations for individual actions and vehicles.

Artificial intelligence (AI) plays a crucial role in autonomous driving (AD) research, propelling its development towards intelligence and efficiency. Currently, the development of AD technology follows two main technical paths: modularization and end-to-end. Modularization decompose the driving task into modules such as perception, prediction, planning, and control, and train them separately. Due to the inconsistency of training objectives between modules, the integrated effect suffers from bias. End-to-end attempts to address this issue by utilizing a single model that directly maps from sensor data to control signals. This path has limited learning capabilities in a comprehensive set of features and struggles to handle unpredictable long-tail events and complex urban traffic scenarios. In the face of challenges encountered in both paths, many researchers believe that large language models (LLMs) with powerful reasoning capabilities and extensive knowledge understanding may be the solution, expecting LLMs to provide AD systems with deeper levels of understanding and decision-making capabilities. In light of the challenges faced by both paths, many researchers believe that LLMs, with their powerful reasoning abilities and extensive knowledge, could offer a solution. To understand if LLMs could enhance AD, this paper conducts a thorough analysis of the potential applications of LLMs in AD systems, including exploring their optimization strategies in both modular and end-to-end approaches, with a particular focus on how LLMs can tackle the problems and challenges present in current solutions. Furthermore, we discuss an important question: Can LLM-based artificial general intelligence (AGI) be a key to achieve high-level AD? We further analyze the potential limitations and challenges that LLMs may encounter in promoting the development of AD technology.

Despite the popularity of multi-agent reinforcement learning (RL) in simulated and two-player applications, its success in messy real-world applications has been limited. A key challenge lies in its generalizability across problem variations, a common necessity for many real-world problems. Contextual reinforcement learning (CRL) formalizes learning policies that generalize across problem variations. However, the lack of standardized benchmarks for multi-agent CRL has hindered progress in the field. Such benchmarks are desired to be based on real-world applications to naturally capture the many open challenges of real-world problems that affect generalization. To bridge this gap, we propose IntersectionZoo, a comprehensive benchmark suite for multi-agent CRL through the real-world application of cooperative eco-driving in urban road networks. The task of cooperative eco-driving is to control a fleet of vehicles to reduce fleet-level vehicular emissions. By grounding IntersectionZoo in a real-world application, we naturally capture real-world problem characteristics, such as partial observability and multiple competing objectives. IntersectionZoo is built on data-informed simulations of 16,334 signalized intersections derived from 10 major US cities, modeled in an open-source industry-grade microscopic traffic simulator. By modeling factors affecting vehicular exhaust emissions (e.g., temperature, road conditions, travel demand), IntersectionZoo provides one million data-driven traffic scenarios. Using these traffic scenarios, we benchmark popular multi-agent RL and human-like driving algorithms and demonstrate that the popular multi-agent RL algorithms struggle to generalize in CRL settings. Having demonstrated impressive performance in simulated multi-agent applications such as Starcraft (Samvelyan et al., 2019), RL holds potential for various multi-agent real-world applications including autonomous driving (Kiran et al., 2021), robotic warehousing (Bahrpeyma & Reichelt, 2022), and traffic control (Wu et al., 2021). However, compared to simulated applications, the success of RL in real-world applications has been rather limited (Dulac-Arnold et al., 2021). A key challenge lies in making RL algorithms generalize across problem variations, such as when weather conditions change in autonomous driving.

Mixed Integer Linear Programming (MILP) is essential for modeling complex decision-making problems but faces challenges in computational tractability and requires expert formulation. Current deep learning approaches for MILP focus on specific problem classes and do not generalize to unseen classes. To address this shortcoming, we take a foundation model training approach, where we train a single deep learning model on a diverse set of MILP problems to generalize across problem classes. As existing datasets for MILP lack diversity and volume, we introduce MILP-Evolve, a novel LLM-based evolutionary framework that is capable of generating a large set of diverse MILP classes with an unlimited amount of instances. We study our methodology on three key learning tasks that capture diverse aspects of MILP: (1) integrality gap prediction, (2) learning to branch, and (3) a new task of aligning MILP instances with natural language descriptions. Our empirical results show that models trained on the data generated by MILP-Evolve achieve significant improvements on unseen problems, including MIPLIB benchmarks. Our work highlights the potential of moving towards a foundation model approach for MILP that can generalize to a broad range of MILP applications. We are committed to fully open-sourcing our work to advance further research.

Fleets of autonomous vehicles can mitigate traffic congestion through simple actions, thus improving many socioeconomic factors such as commute time and gas costs. However, these approaches are limited in practice as they assume precise control over autonomous vehicle fleets, incur extensive installation costs for a centralized sensor ecosystem, and also fail to account for uncertainty in driver behavior. To this end, we develop a class of learned residual policies that can be used in cooperative advisory systems and only require the use of a single vehicle with a human driver. Our policies advise drivers to behave in ways that mitigate traffic congestion while accounting for diverse driver behaviors, particularly drivers' reactions to instructions, to provide an improved user experience. To realize such policies, we introduce an improved reward function that explicitly addresses congestion mitigation and driver attitudes to advice. We show that our residual policies can be personalized by conditioning them on an inferred driver trait that is learned in an unsupervised manner with a variational autoencoder. Our policies are trained in simulation with our novel instruction adherence driver model, and evaluated in simulation and through a user study (N=16) to capture the sentiments of human drivers. Our results show that our approaches successfully mitigate congestion while adapting to different driver behaviors, with up to 20% and 40% improvement as measured by a combination metric of speed and deviations in speed across time over baselines in our simulation tests and user study, respectively. Our user study further shows that our policies are human-compatible and personalize to drivers.

Conventional control, such as model-based control, is commonly utilized in autonomous driving due to its efficiency and reliability. However, real-world autonomous driving contends with a multitude of diverse traffic scenarios that are challenging for these planning algorithms. Model-free Deep Reinforcement Learning (DRL) presents a promising avenue in this direction, but learning DRL control policies that generalize to multiple traffic scenarios is still a challenge. To address this, we introduce Multi-residual Task Learning (MRTL), a generic learning framework based on multi-task learning that, for a set of task scenarios, decomposes the control into nominal components that are effectively solved by conventional control methods and residual terms which are solved using learning. We employ MRTL for fleet-level emission reduction in mixed traffic using autonomous vehicles as a means of system control. By analyzing the performance of MRTL across nearly 600 signalized intersections and 1200 traffic scenarios, we demonstrate that it emerges as a promising approach to synergize the strengths of DRL and conventional methods in generalizable control.

Anticipating possible future deployment of connected and automated vehicles (CAVs), cooperative autonomous driving at intersections has been studied by many works in control theory and intelligent transportation across decades. Simultaneously, recent parallel works in robotics have devised efficient algorithms for multi-agent path finding (MAPF), though often in environments with simplified kinematics. In this work, we hybridize insights and algorithms from MAPF with the structure and heuristics of optimizing the crossing order of CAVs at signal-free intersections. We devise an optimal and complete algorithm, Order-based Search with Kinematics Arrival Time Scheduling (OBS-KATS), which significantly outperforms existing algorithms, fixed heuristics, and prioritized planning with KATS. The performance is maintained under different vehicle arrival rates, lane lengths, crossing speeds, and control horizon. Through ablations and dissections, we offer insight on the contributing factors to OBS-KATS's performance. Our work is directly applicable to many similarly scaled traffic and multi-robot scenarios with directed lanes.

Emerging mobility systems are increasingly capable of recommending options to mobility users, to guide them towards personalized yet sustainable system outcomes. Even more so than the typical recommendation system, it is crucial to minimize regret, because 1) the mobility options directly affect the lives of the users, and 2) the system sustainability relies on sufficient user participation. In this study, we consider accelerating user preference learning by exploiting a low-dimensional latent space that captures the mobility preferences of users. We introduce a hierarchical contextual bandit framework named Expert with Clustering (EWC), which integrates clustering techniques and prediction with expert advice. EWC efficiently utilizes hierarchical user information and incorporates a novel Loss-guided Distance metric. This metric is instrumental in generating more representative cluster centroids. In a recommendation scenario with $N$ users, $T$ rounds per user, and $K$ options, our algorithm achieves a regret bound of $O(N\sqrt{T\log K} + NT)$. This bound consists of two parts: the first term is the regret from the Hedge algorithm, and the second term depends on the average loss from clustering. The algorithm performs with low regret, especially when a latent hierarchical structure exists among users. This regret bound underscores the theoretical and experimental efficacy of EWC, particularly in scenarios that demand rapid learning and adaptation. Experimental results highlight that EWC can substantially reduce regret by 27.57% compared to the LinUCB baseline. Our work offers a data-efficient approach to capturing both individual and collective behaviors, making it highly applicable to contexts with hierarchical structures. We expect the algorithm to be applicable to other settings with layered nuances of user preferences and information.