What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning
arXiv:1901.01492
Abstract
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
arXiv commentCurrently under review
References in corpus (7)
- The FF Planning System: Fast Plan Generation Through Heuristic Search
- On Evaluation of Embodied Navigation Agents
- Learning to Navigate in Complex Environments
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Gated-Attention Architectures for Task-Oriented Language Grounding
- CHALET: Cornell House Agent Learning Environment