Related papers: From Static Constraints to Dynamic Adaptation: Sam…

We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in…

Deploying reinforcement learning (RL) in robotics, industry, and health care is blocked by two obstacles: the difficulty of specifying accurate rewards and the risk of unsafe, data-hungry exploration. We address this by proposing a…

We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies. DICE-RL turns a pretrained…

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

Inspired by the recent successes of Inverse Optimization (IO) across various application domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for continuous state and action spaces, leveraging the convex loss function…

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

Dynamic radio resource management (RRM) in wireless networks presents significant challenges, particularly in the context of Radio Access Network (RAN) slicing. This technology, crucial for catering to varying user requirements, often…

Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic…

Several approaches have been proposed to improve the sample efficiency of online reinforcement learning (RL) by leveraging demonstrations collected offline. The offline data can be used directly as transitions to optimize RL objectives, or…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

The field of Offline Reinforcement Learning (RL) aims to derive effective policies from pre-collected datasets without active environment interaction. While traditional offline RL algorithms like Conservative Q-Learning (CQL) and Implicit…

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

We introduce DynaMITE-RL, a meta-reinforcement learning (meta-RL) approach to approximate inference in environments where the latent state evolves at varying rates. We model episode sessions - parts of the episode where the latent state is…

Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently…

In many open environment applications, data are collected in the form of a stream, which exhibits an evolving distribution over time. How to design algorithms to track these evolving data distributions with provable guarantees, particularly…

Online Continual Learning (OCL) empowers machine learning models to acquire new knowledge online across a sequence of tasks. However, OCL faces a significant challenge: catastrophic forgetting, wherein the model learned in previous tasks is…

We introduce Dynamic Retrieval-Augmented Expert Networks (DRAE), a groundbreaking architecture that addresses the challenges of lifelong learning, catastrophic forgetting, and task adaptation by combining the dynamic routing capabilities of…

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms take the approach of constraining or regularizing…

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected…