We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the generative and noising processes, using either differentiable simulation or off-policy reinforcement learning (RL). We prove equivalences between families of objectives in the limit of infinitesimal discretization steps, linking entropic RL methods (GFlowNets) with continuous-time objects (partial differential equations and path space measures). We further show that an appropriate choice of coarse time discretization during training allows greatly improved sample efficiency and the use of time-local objectives, achieving competitive performance on standard sampling benchmarks with reduced computational cost.

To achieve high service quality and profitability, meal delivery platforms like Uber Eats and Grubhub must strategically operate their fleets to ensure timely deliveries for current orders while mitigating the consequential impacts of suboptimal decisions that leads to courier understaffing in the future. This study set out to solve the real-time order dispatching and idle courier steering problems for a meal delivery platform by proposing a reinforcement learning (RL)-based strategic dual-control framework. To address the inherent sequential nature of these problems, we model both order dispatching and courier steering as Markov Decision Processes. Trained via a deep reinforcement learning (DRL) framework, we obtain strategic policies by leveraging the explicitly predicted demands as part of the inputs. In our dual-control framework, the dispatching and steering policies are iteratively trained in an integrated manner. These forward-looking policies can be executed in real-time and provide decisions while jointly considering the impacts on local and network levels. To enhance dispatching fairness, we propose convolutional deep Q networks to construct fair courier embeddings. To simultaneously rebalance the supply and demand within the service network, we propose to utilize mean-field approximated supply-demand knowledge to reallocate idle couriers at the local level. Utilizing the policies generated by the RL-based strategic dual-control framework, we find the delivery efficiency and fairness of workload distribution among couriers have been improved, and under-supplied conditions have been alleviated within the service network. Our study sheds light on designing an RL-based framework to enable forward-looking real-time operations for meal delivery platforms and other on-demand services.

Automated Vehicles (AVs) hold promise for revolutionizing transportation by improving road safety, traffic efficiency, and overall mobility. Despite the steady advancement in high-level AVs in recent years, the transition to full automation entails a period of mixed traffic, where AVs of varying automation levels coexist with human-driven vehicles (HDVs). Making AVs socially compliant and understood by human drivers is expected to improve the safety and efficiency of mixed traffic. Thus, ensuring AVs compatibility with HDVs and social acceptance is crucial for their successful and seamless integration into mixed traffic. However, research in this critical area of developing Socially Compliant AVs (SCAVs) remains sparse. This study carries out the first comprehensive scoping review to assess the current state of the art in developing SCAVs, identifying key concepts, methodological approaches, and research gaps. An expert interview was also conducted to identify critical research gaps and expectations towards SCAVs. Based on the scoping review and expert interview input, a conceptual framework is proposed for the development of SCAVs. The conceptual framework is evaluated using an online survey targeting researchers, technicians, policymakers, and other relevant professionals worldwide. The survey results provide valuable validation and insights, affirming the significance of the proposed conceptual framework in tackling the challenges of integrating AVs into mixed-traffic environments. Additionally, future research perspectives and suggestions are discussed, contributing to the research and development agenda of SCAVs.

Cooperative heterogeneous multi-agent tasks require agents to effectively coordinate their behaviors while accounting for their relative capabilities. Learning-based solutions to this challenge span between two extremes: i) shared-parameter methods, which encode diverse behaviors within a single architecture by assigning an ID to each agent, and are sample-efficient but result in limited behavioral diversity; ii) independent methods, which learn a separate policy for each agent, and show greater behavioral diversity but lack sample-efficiency. Prior work has also explored selective parameter-sharing, allowing for a compromise between diversity and efficiency. None of these approaches, however, effectively generalize to unseen agents or teams. We present Capability-Aware Shared Hypernetworks (CASH), a novel architecture for heterogeneous multi-agent coordination that generates sufficient diversity while maintaining sample-efficiency via soft parameter-sharing hypernetworks. Intuitively, CASH allows the team to learn common strategies using a shared encoder, which are then adapted according to the team's individual and collective capabilities with a hypernetwork, allowing for zero-shot generalization to unseen teams and agents. We present experiments across two heterogeneous coordination tasks and three standard learning paradigms (imitation learning, on- and off-policy reinforcement learning). CASH is able to outperform baseline architectures in success rate and sample efficiency when evaluated on unseen teams and agents despite using less than half of the learnable parameters.

Traffic flow prediction remains a cornerstone for intelligent transportation systems ITS, influencing both route optimization and environmental efforts. While Recurrent Neural Networks RNN and traditional Convolutional Neural Networks CNN offer some insights into the spatial temporal dynamics of traffic data, they are often limited when navigating sparse and extended spatial temporal patterns. In response, the CNN-GRUSKIP model emerges as a pioneering approach. Notably, it integrates the GRU-SKIP mechanism, a hybrid model that leverages the Gate Recurrent Unit of GRU capabilities to process sequences with the SKIP feature of ability to bypass and connect longer temporal dependencies, making it especially potent for traffic flow predictions with erratic and extended patterns. Another distinctive aspect is its non-standard 6-layer CNN, meticulously designed for in-depth spatiotemporal correlation extraction. The model comprises (1) the specialized CNN feature extraction, (2) the GRU-SKIP enhanced long-temporal module adept at capturing extended patterns, (3) a transformer module employing encoder-decoder and multi-attention mechanisms to hone prediction accuracy and trim model complexity, and (4) a bespoke prediction module. When tested against real-world datasets from California of Caltrans Performance Measurement System PeMS, specifically PeMS districts 4 and 8, the CNN-GRUSKIP consistently outperformed established models such as ARIMA, Graph Wave Net, HA, LSTM, STGCN, and APTN. With its potent predictive prowess and adaptive architecture, the CNN-GRUSKIP model stands to redefine ITS applications, especially where nuanced traffic dynamics are in play.

Without any assumptions about data generation, multiple causal models may explain our observations equally well. To avoid selecting a single arbitrary model that could result in unsafe decisions if it does not match reality, it is therefore essential to maintain a notion of epistemic uncertainty about our possible candidates. This thesis studies the problem of structure learning from a Bayesian perspective, approximating the posterior distribution over the structure of a causal model, represented as a directed acyclic graph (DAG), given data. It introduces Generative Flow Networks (GFlowNets), a novel class of probabilistic models designed for modeling distributions over discrete and compositional objects such as graphs. They treat generation as a sequential decision making problem, constructing samples of a target distribution defined up to a normalization constant piece by piece. In the first part of this thesis, we present the mathematical foundations of GFlowNets, their connections to existing domains of machine learning and statistics such as variational inference and reinforcement learning, and their extensions beyond discrete problems. In the second part of this thesis, we show how GFlowNets can approximate the posterior distribution over DAG structures of causal Bayesian Networks, along with the parameters of its causal mechanisms, given observational and experimental data.

Communication has been widely employed to enhance multi-agent collaboration. Previous research has typically assumed delay-free communication, a strong assumption that is challenging to meet in practice. However, real-world agents suffer from channel delays, receiving messages sent at different time points, termed {\it{Asynchronous Communication}}, leading to cognitive biases and breakdowns in collaboration. This paper first defines two communication delay settings in MARL and emphasizes their harm to collaboration. To handle the above delays, this paper proposes a novel framework, Communication Delay-tolerant Multi-Agent Collaboration (CoDe). At first, CoDe learns an intent representation as messages through future action inference, reflecting the stable future behavioral trends of the agents. Then, CoDe devises a dual alignment mechanism of intent and timeliness to strengthen the fusion process of asynchronous messages. In this way, agents can extract the long-term intent of others, even from delayed messages, and selectively utilize the most recent messages that are relevant to their intent. Experimental results demonstrate that CoDe outperforms baseline algorithms in three MARL benchmarks without delay and exhibits robustness under fixed and time-varying delays.

Reinforcement learning demonstrated immense success in modelling complex physics-driven systems, providing end-to-end trainable solutions by interacting with a simulated or real environment, maximizing a scalar reward signal. In this work, we propose, building upon previous work, a multi-agent reinforcement learning approach with assignment constraints for reconstructing particle tracks in pixelated particle detectors. Our approach optimizes collaboratively a parametrized policy, functioning as a heuristic to a multidimensional assignment problem, by jointly minimizing the total amount of particle scattering over the reconstructed tracks in a readout frame. To satisfy constraints, guaranteeing a unique assignment of particle hits, we propose a safety layer solving a linear assignment problem for every joint action. Further, to enforce cost margins, increasing the distance of the local policies predictions to the decision boundaries of the optimizer mappings, we recommend the use of an additional component in the blackbox gradient estimation, forcing the policy to solutions with lower total assignment costs. We empirically show on simulated data, generated for a particle detector developed for proton imaging, the effectiveness of our approach, compared to multiple single- and multi-agent baselines. We further demonstrate the effectiveness of constraints with cost margins for both optimization and generalization, introduced by wider regions with high reconstruction performance as well as reduced predictive instabilities. Our results form the basis for further developments in RL-based tracking, offering both enhanced performance with constrained policies and greater flexibility in optimizing tracking algorithms through the option for individual and team rewards.

Reinforcement Learning from Human Feedback (RLHF) has recently surged in popularity, particularly for aligning large language models and other AI systems with human intentions. At its core, RLHF can be viewed as a specialized instance of Preference-based Reinforcement Learning (PbRL), where the preferences specifically originate from human judgments rather than arbitrary evaluators. Despite this connection, most existing approaches in both RLHF and PbRL primarily focus on optimizing a mean reward objective, neglecting scenarios that necessitate risk-awareness, such as AI safety, healthcare, and autonomous driving. These scenarios often operate under a one-episode-reward setting, which makes conventional risk-sensitive objectives inapplicable. To address this, we explore and prove the applicability of two risk-aware objectives to PbRL: nested and static quantile risk objectives. We also introduce Risk-Aware-PbRL (RA-PbRL), an algorithm designed to optimize both nested and static objectives. Additionally, we provide a theoretical analysis of the regret upper bounds, demonstrating that they are sublinear with respect to the number of episodes, and present empirical results to support our findings.

Developing a reinforcement learning (RL) agent often involves identifying values for numerous parameters, covering the policy, reward function, environment, and agent-internal architecture. Since these parameters are interrelated in complex ways, optimizing them is a black-box problem that proves especially challenging for nonexperts. Although existing optimization-as-a-service platforms (e.g., Vizier and Optuna) can handle such problems, they are impractical for RL systems, since the need for manual user mapping of each parameter to distinct components makes the effort cumbersome. It also requires understanding of the optimization process, limiting the systems' application beyond the machine learning field and restricting access in areas such as cognitive science, which models human decision-making. To tackle these challenges, the paper presents AgentForge, a flexible low-code platform to optimize any parameter set across an RL system. Available at https://github.com/feferna/AgentForge, it allows an optimization problem to be defined in a few lines of code and handed to any of the interfaced optimizers. With AgentForge, the user can optimize the parameters either individually or jointly. The paper presents an evaluation of its performance for a challenging vision-based RL problem.