Related papers: Improving monotonic optimization in heterogeneous …
In edge computing systems, autonomous agents must make fast local decisions while competing for shared resources. Existing MARL methods often resume to centralized critics or frequent communication, which fail under limited observability…
Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic…
The framework of mixed observable Markov decision processes (MOMDP) models many robotic domains in which some state variables are fully observable while others are not. In this work, we identify a significant subclass of MOMDPs defined by…
Solving partially observable Markov decision processes (POMDPs) remains a fundamental challenge in reinforcement learning (RL), primarily due to the curse of dimensionality induced by the non-stationarity of optimal policies. In this work,…
Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) -- the problem of evaluating a new policy using the historical data…
A multiple objective simulation optimization algorithm named Multiple Objective Probabilistic Branch and Bound with Single Observation (MOPBnB(so)) is presented for approximating the Pareto optimal set and the associated efficient frontier…
Recent renewed interest in multi-agent reinforcement learning (MARL) has generated an impressive array of techniques that leverage deep reinforcement learning, primarily actor-critic architectures, and can be applied to a limited range of…
Multi-Agent Reinforcement Learning (MARL) has emerged as a powerfulparadigm for cooperative decision-making in connected autonomous vehicles(CAVs); however, existing approaches often fail to guarantee stability, optimality,and…
Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing state-of-the-art methods face challenges related to sample complexity, training instability, and the risk of…
Multi-objective reinforcement learning (MORL) is essential for addressing the intricacies of real-world RL problems, which often require trade-offs between multiple utility functions. However, MORL is challenging due to unstable learning…
Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the…
Agent-based models (ABMs) have shown promise for modelling various real world phenomena incompatible with traditional equilibrium analysis. However, a critical concern is the manual definition of behavioural rules in ABMs. Recent…
Policy gradient methods can solve complex tasks but often fail when the dimensionality of the action-space or objective multiplicity grow very large. This occurs, in part, because the variance on score-based gradient estimators scales…
In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Given the goal of…
This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous…
Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a…
Reinforcement learning (RL) has achieved remarkable success in a wide range of control and decision-making tasks. However, RL agents often exhibit unstable or degraded performance when deployed in environments subject to unexpected external…
In this paper, we propose a maximum mutual information (MMI) framework for multi-agent reinforcement learning (MARL) to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the mutual information…
The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic…
Heterogeneity is a fundamental property in multi-agent reinforcement learning (MARL), which is closely related not only to the functional differences of agents, but also to policy diversity and environmental interactions. However, the MARL…