Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph
This addresses generalization challenges in goal-driven AI for robotics and navigation, but it is incremental as it builds on hierarchical RL.
The authors tackled partially observable goal-driven tasks like visual navigation by proposing a two-layer hierarchical reinforcement learning method with a Goals Relational Graph, which improved generalization to unseen environments and goals.
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.