Explicit-Implicit Subgoal Planning for Long-Horizon Tasks with Sparse Rewards
Wang, Fangyuan Duan, Anqing Zhou, Peng Huo, Shengzeng Guo, Guodong Yang, Chenguang
Wang, Fangyuan
Duan, Anqing
Zhou, Peng
Huo, Shengzeng
Guo, Guodong
Yang, Chenguang
Supervisor
Department
Robotics
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The challenges inherent in long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To address these challenges, we have developed a novel algorithm, termed hlexplicit-implicit subgoal planning (EISP), designed to tackle long-horizon tasks through a divide-and-conquer approach. We utilize two primary criteria, feasibility and optimality, to ensure the quality of the generated subgoals. EISP consists of three components: a hybrid subgoal generator, a hindsight sampler, and a value selector. The hybrid subgoal generator uses an explicit model to infer subgoals and an implicit model to predict the final goal, inspired by way of human thinking that infers subgoals by using the current state and final goal as well as reason about the final goal conditioned on the current state and given subgoals. Additionally, the hindsight sampler selects valid subgoals from an offline dataset to enhance the feasibility of the generated subgoals. While the value selector utilizes the value function in reinforcement learning to filter the optimal subgoals from subgoal candidates. To validate our method, we conduct four long-horizon tasks in both simulation and the real world. The obtained quantitative and qualitative data indicate that our approach achieves promising performance compared to other baseline methods.
Citation
F. Wang et al., “Explicit-Implicit Subgoal Planning for Long-Horizon Tasks With Sparse Rewards,” IEEE Transactions on Automation Science and Engineering, vol. 22, pp. 16038–16049, Jan. 2025, doi: 10.1109/TASE.2025.3574162.
Source
IEEE Transactions on Automation Science and Engineering
Conference
Keywords
Learning control systems, Manipulator motion-planning, Motion control, Motion-planning
Subjects
Source
Publisher
IEEE