Related papers: Learning to Simulate Self-Driven Particles System …

Learning cooperative multi-agent policies directly from high-dimensional, multimodal sensory inputs like pixels and audio (from pixels) is notoriously sample-inefficient. Model-free Multi-Agent Reinforcement Learning (MARL) algorithms…

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced…

Reinforcement learning (RL) is currently one of the most prominent methods for optimizing dynamical systems, with breakthrough results across various fields. The framework is based on the concept of a Markov decision process (MDP), leading…

Multi-agent reinforcement learning (MARL) holds substantial promise for intelligent decision-making in complex environments. However, it suffers from a coordination and scalability bottleneck as the number of agents increases. To address…

Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov…

Distributed learning is essential to train machine learning algorithms across heterogeneous agents while maintaining data privacy. We conduct an asymptotic analysis of Unified Distributed SGD (UD-SGD), exploring a variety of communication…

This paper introduces SPIRAL (Self-Play Incremental Racing Algorithm for Learning), a novel approach for training autonomous drones in multi-agent racing competitions. SPIRAL distinctively employs a self-play mechanism to incrementally…

Human intervention is an effective way to inject human knowledge into the training loop of reinforcement learning, which can bring fast learning and ensured training safety. Given the very limited budget of human intervention, it remains…

The field of Multi-Agent System (MAS) is an active area of research within Artificial Intelligence, with an increasingly important impact in industrial and other real-world applications. Within a MAS, autonomous agents interact to pursue…

We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification…

Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive…

The decision and planning system for autonomous driving in urban environments is hard to design. Most current methods manually design the driving policy, which can be expensive to develop and maintain at scale. Instead, with imitation…

Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently…

We introduce the novel concept of Spatial Predictive Control (SPC) to solve the following problem: given a collection of agents (e.g., drones) with positional low-level controllers (LLCs) and a mission-specific distributed cost function,…

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…

Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…

Modular robots can be reconfigured to create a variety of designs from a small set of components. But constructing a robot's hardware on its own is not enough -- each robot needs a controller. One could create controllers for some designs…

Offline multi-agent reinforcement learning (MARL) enables policy learning from fixed datasets, but is prone to coordination failure: agents trained on static, off-policy data converge to suboptimal joint behaviours because they cannot…

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

Communication technologies enable coordination among connected and autonomous vehicles (CAVs). However, it remains unclear how to utilize shared information to improve the safety and efficiency of the CAV system in dynamic and complicated…