7 accepted papers
Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation for downstream control tasks. Despite recent progress, we argue that current off-policy URL methods are limited by two critical, overlooked bottlenecks:…
Existing offline hierarchical reinforcement learning methods rely on high-level policy learning to generate subgoal sequences. However, their efficiency degrades as task horizons increase, and they lack effective strategies for stitching useful state transitions across different trajectories. We pro…
Model-based reinforcement learning (MBRL) has been used to efficiently solve vision-based control tasks in high-dimensional image observations. Although recent MBRL algorithms perform well in trained observations, they fail when faced with visual distractions in observations. These task-irrelevant d…
Reinforcement learning (RL) has achieved considerable success in many fields, but applying it to real-world problems can be costly and risky because it requires a lot of online interaction. Recently, offline RL has shown the possibility of extracting a solution through existing logged data without o…
Neurological diseases affect more than 50 million people living with persistent upper limb impairments worldwide, and 40% of patients remain impaired even after intensive hospital care. Wearable robots have been developed for enhancing functionality in activities of daily living (ADL). The role of f
Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light. It becomes more important if those distractions are not exposed during training…
The cable-driven mechanism is frequently used in many mechanical systems and usually requires one motor for each cable. If the system controls multiple cables, additional components in the motor system can increase the overall mass and volume, making the system less compact. Differential mechanisms