Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation

2019-10-19Code Available0· sign in to hype

Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Juan Rojas, Paul Weng

Code Available — Be the first to reproduce this paper.

Code

github.com/YijiongLin/ITER_KER_GER
Officialtf★ 0

Abstract

Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed.

Tasks

Data Augmentation Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation

Code

Abstract

Tasks

Reproductions