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

Abstract

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 highlevel 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 1 .

Knowledge driven indoor object‐goal navigation aid for visually impaired people

“…and Ye et al. [7–9, 31–35] conducted an in‐depth study on encoding prior knowledge into the DRL model for object‐goal navigation. However, in the analysis of Mishkin et al.…”