Related papers: Sparse shepherding control of large-scale multi-ag…

We address the problem of controlling the density of a large ensemble of follower agents by acting on a group of leader agents that interact with them. Using coupled partial integro-differential equations to describe leader and follower…

This study proposes the use of a social learning method to estimate a global state within a multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a partially observable environment. We assume that the…

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to…

A major challenge in real-world reinforcement learning (RL) is the sparsity of reward feedback. Often, what is available is an intuitive but sparse reward function that only indicates whether the task is completed partially or fully.…

Reinforcement learning solely from an agent's self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done right, agents learning from real data can be surprisingly…

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…

We analyze the problem of controlling a multi-agent system with additive white noise through parsimonious interventions on a selected subset of the agents (leaders). For such a controlled system with a SDE constraint, we introduce a…

Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making…

Traditional planning and control methods could fail to find a feasible trajectory for an autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle-free volume in spacetime is very small in these scenarios…

Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample efficiency. Recent…

Control of distributed parameter systems affected by delays is a challenging task, particularly when the delays depend on spatial variables. The idea of integrating analytical control theory with learning-based control within a unified…

A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement learning, sparse coding…

Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing methods for addressing this issue either control policy to…

For high dimensional particle systems, governed by smooth nonlinearities depending on mutual distances between particles, one can construct low-dimensional representations of the dynamical system, which allow the learning of nearly optimal…

Multiple systems estimation strategies have recently been applied to quantify hard-to-reach populations, particularly when estimating the number of victims of human trafficking and modern slavery. In such contexts, it is not uncommon to see…

Controlling systems governed by partial differential equations is an inherently hard problem. Specifically, control of wave dynamics is challenging due to additional physical constraints and intrinsic properties of wave phenomena such as…

Successfully navigating a complex environment to obtain a desired outcome is a difficult task, that up to recently was believed to be capable only by humans. This perception has been broken down over time, especially with the introduction…

Various congestion control protocols have been designed to achieve high performance in different network environments. Modern online learning solutions that delegate the congestion control actions to a machine cannot properly converge in…

Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks.…

Nowadays, model-free reinforcement learning algorithms have achieved remarkable performance on many decision making and control tasks, but high sample complexity and low sample efficiency still hinder the wide use of model-free…