Robotic Table Tennis with Model-Free Reinforcement Learning

TL;DR

This paper introduces a model-free reinforcement learning approach for robotic table tennis, achieving high return rates and multi-modal stroke styles without architectural priors.

Contribution

It demonstrates that evolutionary search with CNN-based policies can learn smooth, multi-modal control strategies for fast robotic table tennis without prior architectural constraints.

Findings

Achieved 80% return rate on diverse ball throws

Developed multi-modal forehand and backhand strokes

Learned smooth, efficient policies at 100Hz control rate

Abstract

We propose a model-free algorithm for learning efficient policies capable of returning table tennis balls by controlling robot joints at a rate of 100Hz. We demonstrate that evolutionary search (ES) methods acting on CNN-based policy architectures for non-visual inputs and convolving across time learn compact controllers leading to smooth motions. Furthermore, we show that with appropriately tuned curriculum learning on the task and rewards, policies are capable of developing multi-modal styles, specifically forehand and backhand stroke, whilst achieving 80\% return rate on a wide range of ball throws. We observe that multi-modality does not require any architectural priors, such as multi-head architectures or hierarchical policies.