VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation
This addresses navigation efficiency for AI agents in photorealistic environments, though it appears incremental as it builds on existing Universal Successor Features and A3C methods.
The paper tackled target-driven visual navigation by developing VUSFA, a transfer reinforcement learning approach that achieved state-of-the-art performance with greater training stability and improved transfer learning ability in the AI2THOR simulator.
In this paper, we show how novel transfer reinforcement learning techniques can be applied to the complex task of target driven navigation using the photorealistic AI2THOR simulator. Specifically, we build on the concept of Universal Successor Features with an A3C agent. We introduce the novel architectural contribution of a Successor Feature Dependant Policy (SFDP) and adopt the concept of Variational Information Bottlenecks to achieve state of the art performance. VUSFA, our final architecture, is a straightforward approach that can be implemented using our open source repository. Our approach is generalizable, showed greater stability in training, and outperformed recent approaches in terms of transfer learning ability.