Related papers: Guardian: Decoupling Exploration from Safety in Re…
Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions,…
Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…
Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the sense that they…
There have been attempts in reinforcement learning to exploit a priori knowledge about the structure of the system. This paper proposes a hybrid reinforcement learning controller which dynamically interpolates a model-based linear…
Autonomous Cyber Operations (ACO) rely on Reinforcement Learning (RL) to train agents to make effective decisions in the cybersecurity domain. However, existing ACO applications require agents to learn from scratch, leading to slow…
While offline reinforcement learning provides reliable policies for real-world deployment, its inherent pessimism severely restricts an agent's ability to explore and collect novel data online. Drawing inspiration from safe reinforcement…
We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are…
Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to…
Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…
Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system…
This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…
We study offline multi-agent reinforcement learning (RL) in Markov games, where the goal is to learn an approximate equilibrium -- such as Nash equilibrium and (Coarse) Correlated Equilibrium -- from an offline dataset pre-collected from…
Reinforcement learning (RL) has been widely adopted for controlling and optimizing complex engineering systems such as next-generation wireless networks. An important challenge in adopting RL is the need for direct access to the physical…
Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation,…
Offline-to-Online Reinforcement Learning (O2O RL) faces a critical dilemma in balancing the use of a fixed offline dataset with newly collected online experiences. Standard methods, often relying on a fixed data-mixing ratio, struggle to…
Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy…
Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…
Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models…
Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL): (1) slow multi-turn interactions with GUI environments for…
Offline-to-online reinforcement learning (O2O RL) aims to obtain a continually improving policy as it interacts with the environment, while ensuring the initial policy behaviour is satisficing. This satisficing behaviour is necessary for…