Hierarchical Reinforcement Learning By Discovering Intrinsic Options
This addresses the challenge of sample inefficiency and task-specific assumptions in hierarchical RL for robotics and navigation, though it appears incremental as it builds on existing hierarchical RL frameworks.
The paper tackles the problem of learning hierarchical reinforcement learning (RL) with task-agnostic options in sparse-reward environments, achieving higher success rates and greater sample efficiency compared to regular RL and state-of-the-art hierarchical RL methods.
We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-agnostic options in a self-supervised manner while jointly learning to utilize them to solve sparse-reward tasks. Unlike current hierarchical RL approaches that tend to formulate goal-reaching low-level tasks or pre-define ad hoc lower-level policies, HIDIO encourages lower-level option learning that is independent of the task at hand, requiring few assumptions or little knowledge about the task structure. These options are learned through an intrinsic entropy minimization objective conditioned on the option sub-trajectories. The learned options are diverse and task-agnostic. In experiments on sparse-reward robotic manipulation and navigation tasks, HIDIO achieves higher success rates with greater sample efficiency than regular RL baselines and two state-of-the-art hierarchical RL methods.