Related papers: Approximate Model-Based Shielding for Safe Reinfor…
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…
Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…
Reinforcement learning (RL) has achieved enormous progress in solving various sequential decision-making problems, such as control tasks in robotics. Since policies are overfitted to training environments, RL methods have often failed to be…
We propose a new model-based offline RL framework, called Adversarial Models for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon an arbitrary baseline policy regardless of data coverage. Based on…
Safe reinforcement learning (Safe RL) refers to a class of techniques that aim to prevent RL algorithms from violating constraints in the process of decision-making and exploration during trial and error. In this paper, a novel model-free…
Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…
Ensuring safety in autonomous driving (AD) remains a significant challenge, especially in highly dynamic and complex traffic environments where diverse agents interact and unexpected hazards frequently emerge. Traditional reinforcement…
Reinforcement learning (RL)-based methods have achieved significant success in managing grid-interactive efficient buildings (GEBs). However, RL does not carry intrinsic guarantees of constraint satisfaction, which may lead to severe safety…
Imitation of expert behaviour is a highly desirable and safe approach to the problem of sequential decision making. We provide an easy-to-implement, novel algorithm for imitation learning under a strict data paradigm, in which the agent…
Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL) have emerged as promising methodologies for addressing challenges in automated cyber defence (ACD). These techniques offer adaptive decision-making capabilities in…
Reinforcement learning (RL) has shown great promise in simulated environments, such as games, where failures have minimal consequences. However, the deployment of RL agents in real-world systems such as autonomous vehicles, robotics, UAVs,…
Reinforcement learning (RL) agents need to explore their environment to learn optimal behaviors and achieve maximum rewards. However, exploration can be risky when training RL directly on real systems, while simulation-based training…
Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting.…
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world…
Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional…
Ensuring safety is important for the practical deployment of reinforcement learning (RL). Various challenges must be addressed, such as handling stochasticity in the environments, providing rigorous guarantees of persistent state-wise…
Robust reinforcement learning (RL) aims to find a policy that optimizes the worst-case performance in the face of uncertainties. In this paper, we focus on action robust RL with the probabilistic policy execution uncertainty, in which,…
Approximate Computing (AxC) techniques have become increasingly popular in trading off accuracy for performance gains in various applications. Selecting the best AxC techniques for a given application is challenging. Among proposed…
Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a safety guide based on model predictive control (MPC) with a…
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional…