相关论文: A New Formalism, Method and Open Issues for Zero-S…

Despite the impressive recent advances in learning-based robot control, ensuring robustness to out-of-distribution conditions remains an open challenge. Safety filters can, in principle, keep arbitrary control policies from incurring…

We investigate a co-design problem, encompassing simultaneous design of system infrastructure and control, through a game-theoretical framework. To this end, we propose the co-design problem as a two-layer hierarchical strategic…

Since federated learning (FL) has been introduced as a decentralized learning technique with privacy preservation, statistical heterogeneity of distributed data stays the main obstacle to achieve robust performance and stable convergence in…

This paper proposes a label-free controller for a second-order multi-agent system to cooperatively fence a moving target of variational velocity into a convex hull formed by the agents whereas maintaining a rigid formation. Therein, no…

Although multi-agent reinforcement learning can tackle systems of strategically interacting entities, it currently fails in scalability and lacks rigorous convergence guarantees. Crucially, learning in multi-agent systems can become…

Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-time. While conventional RL optimizes policies for fixed…

Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes the gap by…

In this article, we consider a fundamental decentralized optimal control problem, which we call the two-player problem. Two subsystems are interconnected in a nested information pattern, and output feedback controllers must be designed for…

This paper investigates the leader-following consensus problem for a class of multi-agent systems subject to adversarial attack-like external inputs. To address this, we formulate the robust leader-following control problem as a global…

We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a…

Zero-shot learning (ZSL) methods have been studied in the unrealistic setting where test data are assumed to come from unseen classes only. In this paper, we advocate studying the problem of generalized zero-shot learning (GZSL) where the…

In the context of multi-player, general-sum games, there is an increasing interest in solution concepts modeling some form of communication among players, since they can lead to socially better outcomes with respect to Nash equilibria, and…

Multi-Agent Reinforcement Learning (MARL) comprises an area of growing interest in the field of machine learning. Despite notable advances, there are still problems that require investigation. The lazy agent pathology is a famous problem in…

Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the…

This paper extends the notion of learning equilibrium in game theory from matrix games to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that converges to a Tit-for-Tat behavior. It allows cooperative…

Safe and efficient autonomous driving in dense traffic is fundamentally a decentralized multi-agent coordination problem, where interactions at conflict points such as merging and weaving must be resolved reliably under partial…

In open-world learning, an agent starts with a set of known classes, detects, and manages things that it does not know, and learns them over time from a non-stationary stream of data. Open-world learning is related to but also distinct from…

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the…

We provide a general approach to reformulating any continuous-time stochastic Stackelberg differential game under closed-loop strategies as a single-level optimisation problem with target constraints. More precisely, we consider a…

We study decentralized multi-agent coordination where agents must correlate actions against an unobserved field and cannot communicate. To isolate correlation geometry from payoff optimization, we introduce the Hidden-Field Coordination…