Related papers: Asynchronous Agents with Perfect Recall: Model Red…

Two-player (antagonistic) games on (possibly stochastic) graphs are a prevalent model in theoretical computer science, notably as a framework for reactive synthesis. Optimal strategies may require randomisation when dealing with inherently…

The goal of agents in multi-agent environments is to maximize total reward against the opposing agents that are encountered. Following a game-theoretic solution concept, such as Nash equilibrium, may obtain a strong performance in some…

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

Deep Reinforcement Learning agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training on new data. Replay Memories are a common solution to the problem, decorrelating…

Tasks where the set of possible actions depend discontinuously on the state pose a significant challenge for current reinforcement learning algorithms. For example, a locked door must be first unlocked, and then the handle turned before the…

Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study…

In multi-agent systems, agents need to interact and collaborate with other agents in environments. Agent modeling is crucial to facilitate agent interactions and make adaptive cooperation strategies. However, it is challenging for agents to…

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL),…

We consider the problem where $M$ agents interact with $M$ identical and independent environments with $S$ states and $A$ actions using reinforcement learning for $T$ rounds. The agents share their data with a central server to minimize…

Many real-world scenarios involve teams of agents that have to coordinate their actions to reach a shared goal. We focus on the setting in which a team of agents faces an opponent in a zero-sum, imperfect-information game. Team members can…

We investigate uniformity properties of strategies. These properties involve sets of plays in order to express useful constraints on strategies that are not \mu-calculus definable. Typically, we can state that a strategy is…

Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However, current cooperative multi-agent reinforcement learning…

Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning (MARL). To be effective, credit assignment methods must preserve the environment's…

Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks and has become the state-of-the-art for visual object tracking. The model stores information from previous frames in a memory bank, enabling…

Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current…

While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents…

Expressing attack-defence trees in a multi-agent setting allows for studying a new aspect of security scenarios, namely how the number of agents and their task assignment impact the performance, e.g. attack time, of strategies executed by…

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of…

While deep reinforcement learning has shown important empirical success, it tends to learn relatively slow due to slow propagation of rewards information and slow update of parametric neural networks. Non-parametric episodic memory, on the…

While Visual Multi-Agent Systems (VMAS) promise to enhance comprehensive abilities through inter-agent collaboration, empirical evidence reveals a counter-intuitive "scaling wall": increasing agent turns often degrades performance while…