Relay hindsight experience replay: Self-guided continual reinforcement learning for sequential object manipulation tasks with sparse rewards

Y Luo, Y Wang, K Dong, Q Zhang, E Cheng, Z Sun… - Neurocomputing, 2023 - Elsevier
Learning with sparse rewards remains a challenging problem in reinforcement learning
(RL). In particular, for sequential object manipulation tasks, the RL agent generally only …

Efficient multi-task and transfer reinforcement learning with parameter-compositional framework

L Sun, H Zhang, W Xu… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
In this work, we investigate the potential of improving multi-task training and also leveraging
it for transferring in the reinforcement learning setting. We identify several challenges …

[PDF][PDF] Autonomous Skill Acquisition for Robots Using Graduated Learning

G Vasan - Proceedings of the 23rd International Conference on …, 2024 - ifaamas.org
Skill acquisition is among the most remarkable aspects of human intelligence. It involves
discovering purposeful behavioural modules, retaining them as skills, honing them through …

DexV2A: vision pretraining for dexterous manipulation

AH Stoken - 2022 - repositories.lib.utexas.edu
Achieving human-like dexterity for common daily tasks with a robotic hand is a challenging
task for reinforcement learning. To combat the high dimensionality of the state-action space …