DeepAI
Log In Sign Up

VUSFA:Variational Universal Successor Features Approximator to Improve Transfer DRL for Target Driven Visual Navigation

08/18/2019
by   Shamane Siriwardhana, et al.
0

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.

READ FULL TEXT
04/20/2021

Visual Navigation with Spatial Attention

This work focuses on object goal visual navigation, aiming at finding th...
01/09/2023

Network Slicing via Transfer Learning aided Distributed Deep Reinforcement Learning

Deep reinforcement learning (DRL) has been increasingly employed to hand...
05/28/2022

Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

Recent progress in deep model-based reinforcement learning allows agents...
06/04/2020

Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion

We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO...
02/07/2018

A Critical Investigation of Deep Reinforcement Learning for Navigation

The navigation problem is classically approached in two steps: an explor...
09/30/2020

Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning

We present a target-driven navigation system to improve mapless visual n...
08/13/2021

Reinforcement Learning for Robot Navigation with Adaptive ExecutionDuration (AED) in a Semi-Markov Model

Deep reinforcement learning (DRL) algorithms have proven effective in ro...