What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning
This addresses the problem of inefficient long-term planning in reinforcement learning for AI researchers and practitioners, offering a novel integration that improves performance in visual tasks.
The paper tackles the challenge of long-term planning in reinforcement learning, especially in dynamic visual environments, by proposing HIP-RL, a method that combines symbolic planning with deep reinforcement learning, achieving state-of-the-art results on three datasets with fewer steps and training iterations.
Long-term planning poses a major difficulty to many reinforcement learning algorithms. This problem becomes even more pronounced in dynamic visual environments. In this work we propose Hierarchical Planning and Reinforcement Learning (HIP-RL), a method for merging the benefits and capabilities of Symbolic Planning with the learning abilities of Deep Reinforcement Learning. We apply HIPRL to the complex visual tasks of interactive question answering and visual semantic planning and achieve state-of-the-art results on three challenging datasets all while taking fewer steps at test time and training in fewer iterations. Sample results can be found at youtu.be/0TtWJ_0mPfI