Related papers: General and Efficient Visual Goal-Conditioned Rein…

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…

Learning agile humanoid behaviors from human motion offers a powerful route to natural, coordinated control, but existing approaches face a persistent trade-off: reference-tracking policies are often brittle outside the demonstration…

While reinforcement learning provides an appealing formalism for learning individual skills, a general-purpose robotic system must be able to master an extensive repertoire of behaviors. Instead of learning a large collection of skills…

Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown promise by relabeling collected trajectories with achieved…

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not…

Offline reinforcement learning (RL) enables policy optimization using static datasets, avoiding the risks and costs of extensive real-world exploration. However, it struggles with suboptimal offline behaviors and inaccurate value estimation…

In this paper we study how transforming regular reinforcement learning environments into goal-conditioned environments can let agents learn to solve tasks autonomously and reward-free. We show that an agent can learn to solve tasks by…

Conventional supervised learning methods typically assume i.i.d samples and are found to be sensitive to out-of-distribution (OOD) data. We propose Generative Causal Representation Learning (GCRL) which leverages causality to facilitate…

Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems. However, an open question is how to make RL cope with partial observability which is…

Generative models have made significant progress in synthesizing visual content, including images, videos, and 3D/4D structures. However, they are typically trained with surrogate objectives such as likelihood or reconstruction loss, which…

In existing works that learn representation for object detection, the relationship between a candidate window and the ground truth bounding box of an object is simplified by thresholding their overlap. This paper shows information loss in…

Recent approaches have utilized self-supervised auxiliary tasks as representation learning to improve the performance and sample efficiency of vision-based reinforcement learning algorithms in single-agent settings. However, in multi-agent…

Visual understanding is inherently intention-driven - humans selectively focus on different regions of a scene based on their goals. Recent advances in large multimodal models (LMMs) enable flexible expression of such intentions through…

Meta-reinforcement learning (meta-RL) acquires meta-policies that show good performance for tasks in a wide task distribution. However, conventional meta-RL, which learns meta-policies by randomly sampling tasks, has been reported to show…

Continual reinforcement learning aims to sequentially learn a variety of tasks, retaining the ability to perform previously encountered tasks while simultaneously developing new policies for novel tasks. However, current continual RL…

Recent studies on visual reinforcement learning (visual RL) have explored the use of 3D visual representations. However, none of these work has systematically compared the efficacy of 3D representations with 2D representations across…

Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing,…

Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for…

Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recent advancements in MVRL focus on extracting latent…

Dexterous manipulation of arbitrary objects, a fundamental daily task for humans, has been a grand challenge for autonomous robotic systems. Although data-driven approaches using reinforcement learning can develop specialist policies that…