相关论文: Offline Reinforcement Learning with Universal Hori…

Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a…

In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward. In this respect, we develop a novel meta reinforcement learning…

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and nonparametric methods…

Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and…

This paper investigates a hybrid learning framework for reinforcement learning (RL) in which the agent can leverage both an offline dataset and online interactions to learn the optimal policy. We present a unified algorithm and analysis and…

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…

Hierarchical Reinforcement Learning (HRL) approaches have shown successful results in solving a large variety of complex, structured, long-horizon problems. Nevertheless, a full theoretical understanding of this empirical evidence is…

We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Panoramic video provides immersive and interactive experience by enabling humans to control the field of view (FoV) through head movement (HM). Thus, HM plays a key role in modeling human attention on panoramic video. This paper establishes…

Reinforcement Learning (RL) has emerged as the key driver for post-training complex reasoning in Large Language Models (LLMs), yet online RL introduces significant instability and computational overhead. Offline RL offers a compelling…

Methods of deep machine learning enable to to reuse low-level representations efficiently for generating more abstract high-level representations. Originally, deep learning has been applied passively (e.g., for classification purposes).…

Model-based offline reinforcement learning (RL) is a compelling approach that addresses the challenge of learning from limited, static data by generating imaginary trajectories using learned models. However, these approaches often struggle…

In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of…

Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…

Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach…

Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a performance gap on tasks requiring agility. We identify a root cause: in subgoal-based HRL, the…

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as…

Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making. While sensible, this…