Related papers: Rethinking Individual Global Max in Cooperative Mu…
Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a…
Mixed-integer optimization problems arise in a wide range of control applications. Benders decomposition is a widely used algorithm for solving such problems by decomposing them into a mixed-integer master problem and a continuous…
Imitation learning has been applied to a range of robotic tasks, but can struggle when robots encounter edge cases that are not represented in the training data (i.e., distribution shift). Interactive fleet learning (IFL) mitigates…
A major bottleneck in imitation learning is the requirement of a large number of expert demonstrations, which can be expensive or inaccessible. Learning from supplementary demonstrations without strict quality requirements has emerged as a…
Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous challenging domains and environments, but typically require specialized models for each task. In this work, we propose a coherent methodology…
Reinforcement learning faces significant challenges when applied to tasks characterized by sparse reward structures. Although imitation learning, within the domain of supervised learning, offers faster convergence, it relies heavily on…
In cooperative localization, communicating mobile agents use inter-agent relative measurements to improve their dead-reckoning-based global localization. Measurement scheduling enables an agent to decide which subset of available…
The field of cooperative multi-agent reinforcement learning (MARL) has seen widespread use in addressing complex coordination tasks. While value decomposition methods in MARL have been popular, they have limitations in solving tasks with…
In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best…
This paper addresses the limitations of a single agent in task decomposition and collaboration during complex task execution, and proposes a multi-agent architecture for modular task decomposition and dynamic collaboration based on large…
This paper addresses joint target acquisition and position estimation in an OFDM-based integrated sensing and communication (ISAC) network with base station (BS) cooperation via a fusion center. A two-stage framework is proposed: in the…
Multi-task learning is a popular machine learning approach that enables simultaneous learning of multiple related tasks, improving algorithmic efficiency and effectiveness. In the hard parameter sharing approach, an encoder shared through…
In this paper, we study Interaction-Grounded Learning (IGL) [Xie et al., 2021], a paradigm designed for realistic scenarios where the learner receives indirect feedback generated by an unknown mechanism, rather than explicit numerical…
Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently,…
It can largely benefit the reinforcement learning (RL) process of each agent if multiple geographically distributed agents perform their separate RL tasks cooperatively. Different from multi-agent reinforcement learning (MARL) where…
Due to practical constraints such as partial observability and limited communication, Centralized Training with Decentralized Execution (CTDE) has become the dominant paradigm in cooperative Multi-Agent Reinforcement Learning (MARL).…
In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting,…
Federated learning has emerged as a paradigm to train models collaboratively on inherently distributed client data while safeguarding privacy. In this context, personalized federated learning tackles the challenge of data heterogeneity by…
Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be…
Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the model behaves as though it had summarised the context into a population-level statistic…