Related papers: Improved Structural Discovery and Representation L…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

When are multi-agent LLM systems merely a collection of individual agents versus an integrated collective with higher-order structure? We introduce an information-theoretic framework to test -- in a purely data-driven way -- whether…

Trajectory forecasting, or trajectory prediction, of multiple interacting agents in dynamic scenes, is an important problem for many applications, such as robotic systems and autonomous driving. The problem is a great challenge because of…

Deep Reinforcement Learning has made significant progress in multi-agent systems in recent years. In this review article, we have focused on presenting recent approaches on Multi-Agent Reinforcement Learning (MARL) algorithms. In…

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional \textit{sequential} raw data, e.g., video. The framework builds upon recent advances in amortized inference methods…

Machine learning is rapidly being used in database research to improve the effectiveness of numerous tasks included but not limited to query optimization, workload scheduling, physical design, etc. Currently, the research focus has been on…

Understanding the principles of real-world biological multi-agent behaviors is a current challenge in various scientific and engineering fields. The rules regarding the real-world biological multi-agent behaviors such as team sports are…

Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the…

Multi-agent systems (MAS) are foundational in simulating complex real-world scenarios involving autonomous, interacting entities. However, traditional MAS architectures often suffer from rigid coordination mechanisms and difficulty adapting…

This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social environment where agents are deployed, either collaborative,…

Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…

In order to enable high-quality decision making and motion planning of intelligent systems such as robotics and autonomous vehicles, accurate probabilistic predictions for surrounding interactive objects is a crucial prerequisite. Although…

Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of…

In this paper, we investigate a sequential dynamic team problem consisting of two agents with a nested information structure. We use a combination of the person-by-person and prescription approach to derive structural results for optimal…

In this work, we propose a novel memory-based multi-agent meta-learning architecture and learning procedure that allows for learning of a shared communication policy that enables the emergence of rapid adaptation to new and unseen…

Robots that navigate among pedestrians use collision avoidance algorithms to enable safe and efficient operation. Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. However,…

The key challenge in multiagent learning is learning a best response to the behaviour of other agents, which may be non-stationary: if the other agents adapt their strategy as well, the learning target moves. Disparate streams of research…

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor…

This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The…

Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for…