Contrastive Variational Reinforcement Learning for Complex Observations
Xiao Ma, Siwei Chen, David Hsu, Wee Sun Lee
National University of Singapore
Abstract
Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the commonly used generative observation model often does, and is significantly more robust. CVRL achieves comparable performance with state-of-the-art model-based DRL methods on standard Mujoco tasks. It significantly outperforms them on Natural Mujoco tasks and a robot box-pushing task with complex observations, e.g., dynamic shadows.
Paper
Xiao Ma, Siwei Chen, David Hsu, Wee Sun Lee
Contrastive Variational Model-Based Reinforcement Learning for Complex Observations
In Proceedings of 4th Conference on Robot Learning (CoRL), 2020 [PDF][Code]
@inproceedings{ma2020contrastive,
author = {Xiao Ma and Siwei Chen and David Hsu and Wee Sun Lee},
booktitle={Proceedings of the 4th Conference on Robot Learning},
title = {Contrastive Variational Reinforcement Learning for Complex Observations},
year = {2020}
}
Model Overview
Experiment Results
Natural Mujoco Visualizations
Natural Walker Walk
Natural Quadruped Walk
Natural Pendulum Swingup
Natural Cup Catch
Natural Cartpole Balance
Natural Finger Spin
Box Pushing Visualizations
Talk
Related Works
Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee, Nan Ye
Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations
Danijar Hafter, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi
Dream to Control: Learning Behaviors by Latent Imagination