Related papers: Continuous Control Reinforcement Learning: Distrib…

Traditional offline reinforcement learning (RL) methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of…

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Conventional control of fluid systems does not consider system-wide knowledge for optimising energy efficient operation. Distributed control of fluid systems combines reliable local control of components while using system-wide cooperation…

In this paper, we propose a network scenario where the baseband processes of the virtual small cells powered solely by energy harvesters and batteries can be opportunistically executed in a grid-connected edge computing server, co-located…

Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on…

Flow-based policies have recently emerged as a powerful tool in offline and offline-to-online reinforcement learning, capable of modeling the complex, multimodal behaviors found in pre-collected datasets. However, the full potential of…

Inefficient traffic signal control methods may cause numerous problems, such as traffic congestion and waste of energy. Reinforcement learning (RL) is a trending data-driven approach for adaptive traffic signal control in complex urban…

Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications. However, it still suffers from some key limits slowing down its widespread adoption. Its performance is sensitive to initial…

Reinforcement learning has been proven to be highly effective in handling complex control tasks. Traditional methods typically use unimodal distributions, such as Gaussian distributions, to model the output of value distributions. However,…

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion…

To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of…

In this paper we consider the distributed linear quadratic control problem for networks of agents with single integrator dynamics. We first establish a general formulation of the distributed LQ problem and show that the optimal control gain…

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

In this work we augment a Deep Q-Learning agent with a Reward Machine (DQRM) to increase speed of learning vision-based policies for robot tasks, and overcome some of the limitations of DQN that prevent it from converging to good-quality…

Many real-world control problems, ranging from finance to robotics, evolve in continuous time with non-uniform, event-driven decisions. Standard discrete-time reinforcement learning (RL), based on fixed-step Bellman updates, struggles in…

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research. We assume that while…

Model-based Vol/VAR optimization method is widely used to eliminate voltage violations and reduce network losses. However, the parameters of active distribution networks(ADNs) are not onsite identified, so significant errors may be involved…

Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common in realistic tasks to prevent unsafe exploration. To address…

We introduce Diffusion Policy Policy Optimization, DPPO, an algorithmic framework including best practices for fine-tuning diffusion-based policies (e.g. Diffusion Policy) in continuous control and robot learning tasks using the policy…

The learning inefficiency of reinforcement learning (RL) from scratch hinders its practical application towards continuous robotic tracking control, especially for high-dimensional robots. This work proposes a data-informed residual…