Related papers: Learning to Hand Off: Provably Convergent Workflow…

Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learning is unstable in ways that are poorly understood. We study when end-to-end RL training…

While reinforcement learning has been increasingly applied to stochastic control, few studies have systematically examined policy-based methods in queuing environments modeled as a semi-Markov decision process (SMDP). To address this gap,…

We study a decentralized variant of stochastic approximation, a data-driven approach for finding the root of an operator under noisy measurements. A network of agents, each with its own operator and data observations, cooperatively find the…

In this paper, for Markov decision processes (MDPs) with unbounded state spaces we present refined upper bounds presented in [Kara et. al. JMLR'23] on finite model approximation errors via optimizing the quantizers used for finite model…

The integration of large language models (LLMs) into intelligent tutoring systems offers transformative potential for personalized learning in higher education. However, most existing learning path planning approaches lack transparency,…

Multi-agent planning in stochastic environments can be framed formally as a decentralized Markov decision problem. Many real-life distributed problems that arise in manufacturing, multi-robot coordination and information gathering scenarios…

This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent safety constraints. Mathematically, we model the system…

Existing imitation learning methods mainly focus on making an agent effectively mimic a demonstrated behavior, but do not address the potential contradiction between the behavior style and the objective of a task. There is a general lack of…

When reward functions are hand-designed, deep reinforcement learning algorithms often suffer from reward misspecification, causing them to learn suboptimal policies in terms of the intended task objectives. In the single-agent case, inverse…

Active traffic management with autonomous vehicles offers the potential for reduced congestion and improved traffic flow. However, developing effective algorithms for real-world scenarios requires overcoming challenges related to…

We consider synthesis of control policies that maximize the probability of satisfying given temporal logic specifications in unknown, stochastic environments. We model the interaction between the system and its environment as a Markov…

Robots executing iterative tasks in complex, uncertain environments require control strategies that balance robustness, safety, and high performance. This paper introduces a safe information-theoretic learning model predictive control…

Autonomous systems often have logical constraints arising, for example, from safety, operational, or regulatory requirements. Such constraints can be expressed using temporal logic specifications. The system state is often partially…

Cooperation emergence in multi-agent systems represents a fundamental statistical physics problem where microscopic learning rules drive macroscopic collective behavior transitions. We propose a Q-learning-based variant of adaptive rewiring…

The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $\mathcal{S}$ and the action space $\mathcal{A}$ are both finite, to obtain a nearly optimal policy with…

Same-Day Delivery services are becoming increasingly popular in recent years. These have been usually modelled by previous studies as a certain class of Dynamic Vehicle Routing Problem (DVRP) where goods must be delivered from a depot to a…

The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better when they are trained with a larger number of observed tasks…

Multi-agent coordination under partial observability requires agents to share complementary private information. While recent methods optimize messages for intermediate objectives (e.g., reconstruction accuracy or mutual information),…

We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike previous work, our approach allows learning low-level and…

Developing machine learning interatomic potentials (MLIPs) for complex materials systems remains challenging because it requires expertise in atomistic simulations, machine learning, and workflow design, as well as iterative active learning…