Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph

원문 초록

We present a novel two-layer hierarchical reinforcement learning approach equipped with a Goals Relational Graph (GRG) for tackling the partially observable goal-driven task, such as goal-driven visual navigation. Our GRG captures the underlying relations of all goals in the goal space through a Dirichlet-categorical process that facilitates: 1) the high-level network raising a sub-goal towards achieving a designated final goal; 2) the low-level network towards an optimal policy; and 3) the overall system generalizing unseen environments and goals. We evaluate our approach with two settings of partially observable goal-driven tasks -- a grid-world domain and a robotic object search task. Our experimental results show that our approach exhibits superior generalization performance on both unseen environments and new goals.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2506.21039공통 태그 Reinforcement Learning (RL), Hierarchical Reinforcement Learning 등록 2025-06-26

Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning

arXiv:2506.20036공통 태그 Reinforcement Learning (RL), Hierarchical Reinforcement Learning 등록 2025-06-24

Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion

arXiv:2506.14391공통 태그 Reinforcement Learning (RL), Hierarchical Reinforcement Learning 등록 2025-06-17

HiLight: A Hierarchical Reinforcement Learning Framework with Global Adversarial Guidance for Large-Scale Traffic Signal Control

arXiv:cs/9905014공통 태그 Reinforcement Learning (RL), Hierarchical Reinforcement Learning 등록 1999-05-21

토론

이 논문과 연결된 포럼 글이 아직 없습니다.

포럼에서 토론 찾기