相关论文: ME-IGM: Individual-Global-Max in Maximum Entropy M…

We present a comparative study of multi-agent reinforcement learning (MARL) algorithms for cooperative warehouse robotics. We evaluate QMIX and IPPO on the Robotic Warehouse (RWARE) environment and a custom Unity 3D simulation. Our…

Autocurricular training is an important sub-area of multi-agent reinforcement learning~(MARL) that allows multiple agents to learn emergent skills in an unsupervised co-evolving scheme. The robotics community has experimented autocurricular…

In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counterpart of RAML and the entropy regularized reinforcement…

Coordinating actions is the most fundamental form of cooperation in multi-agent reinforcement learning (MARL). Successful decentralized decision-making often depends not only on good individual actions, but on selecting compatible actions…

We study vehicle dispatching in autonomous mobility on demand (AMoD) systems, where a central operator assigns vehicles to customer requests or rejects these with the aim of maximizing its total profit. Recent approaches use multi-agent…

Multi-agent reinforcement learning (MARL) has become effective in tackling discrete cooperative game scenarios. However, MARL has yet to penetrate settings beyond those modelled by team and zero-sum games, confining it to a small subset of…

Multi-agent reinforcement learning (MARL) faces significant challenges in task sequencing and curriculum design, particularly for cooperative coordination scenarios. While curriculum learning has demonstrated success in single-agent…

Researchers have integrated exploration techniques into multi-agent reinforcement learning (MARL) algorithms, drawing on their remarkable success in deep reinforcement learning. Nonetheless, exploration in MARL presents a more substantial…

The recent mean field game (MFG) formalism has enabled the application of inverse reinforcement learning (IRL) methods in large-scale multi-agent systems, with the goal of inferring reward signals that can explain demonstrated behaviours of…

This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself…

Multi-Agent Reinforcement Learning (MARL) is an increasingly important research field that can model and control multiple large-scale autonomous systems. Despite its achievements, existing multi-agent learning methods typically involve…

Multi-agent inverse reinforcement learning (MIRL) can be used to learn reward functions from agents in social environments. To model realistic social dynamics, MIRL methods must account for suboptimal human reasoning and behavior.…

Interactive Imitation Learning (IIL) allows agents to acquire desired behaviors through human interventions, but current methods impose high cognitive demands on human supervisors. We propose the Adaptive Intervention Mechanism (AIM), a…

In this paper, we propose a new mutual information framework for multi-agent reinforcement learning to enable multiple agents to learn coordinated behaviors by regularizing the accumulated return with the simultaneous mutual information…

Episodic rewards present a significant challenge in reinforcement learning. While intrinsic reward methods have demonstrated effectiveness in single-agent rein-forcement learning scenarios, their application to multi-agent reinforcement…

Existing multi-agent reinforcement learning methods are limited typically to a small number of agents. When the agent number increases largely, the learning becomes intractable due to the curse of the dimensionality and the exponential…

We approach the problem of understanding how people interact with each other in collaborative settings, especially when individuals know little about their teammates, via Multiagent Inverse Reinforcement Learning (MIRL), where the goal is…

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which…

Discovering successful coordinated behaviors is a central challenge in Multi-Agent Reinforcement Learning (MARL) since it requires exploring a joint action space that grows exponentially with the number of agents. In this paper, we propose…

Multi-agent Inverse Reinforcement Learning (MAIRL) aims to recover agent reward functions from expert demonstrations. We characterize the feasible reward set in Markov games, identifying all reward functions that rationalize a given…