Target Driven Visual Navigation with Hybrid Asynchronous Universal Successor Representations
arXiv:1811.11312
Abstract
Being able to navigate to a target with minimal supervision and prior knowledge is critical to creating human-like assistive agents. Prior work on map-based and map-less approaches have limited generalizability. In this paper, we present a novel approach, Hybrid Asynchronous Universal Successor Representations (HAUSR), which overcomes the problem of generalizability to new goals by adapting recent work on Universal Successor Representations with Asynchronous Actor-Critic Agents. We show that the agent was able to successfully reach novel goals and we were able to quickly fine-tune the network for adapting to new scenes. This opens up novel application scenarios where intelligent agents could learn from and adapt to a wide range of environments with minimal human input.
arXiv commentDeep Reinforcement Learning Workshop, NeurIPS 2018
References in corpus (5)
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- AI2-THOR: An Interactive 3D Environment for Visual AI
- Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
- Deep Successor Reinforcement Learning
- Universal Successor Representations for Transfer Reinforcement Learning