Robotic Table Tennis with Model-Free Reinforcement Learning
arXiv:2003.14398
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.
arXiv commentV2: new URL of supplementary video. 8 pages, 4 figures
References in corpus (6)
- Continuous control with deep reinforcement learning
- Conditional Image Generation with PixelCNN Decoders
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- Simple random search provides a competitive approach to reinforcement learning
- Model-Free Trajectory-based Policy Optimization with Monotonic Improvement