Recent advancements in deep reinforcement learning (deep RL) has enabled legged robots to learn many agile skills through automated environment interactions. In the past few years, researchers have greatly improved sample efficiency by using off-policy data, imitating animal behaviors, or performing meta learning. Posted by Yuxiang Yang and Deepali Jain, AI Residents, Robotics at Google.
However, sample efficiency remains a bottleneck for most deep reinforcement learning algorithms, especially in the legged locomotion domain.
The authors present two projects that aim to address the above problems and help close the perception-actuation loop for legged robots.
- In Data Efficient Reinforcement Learning for Legged Robots, they present an efficient way to learn low level motion control policies.
- Going beyond simple behaviors, we explore automatic path navigation in Hierarchical Reinforcement Learning for Quadruped Locomotion
Reinforcement learning poses a promising future for robotics by automating the controller design process. With model-based RL, we enabled efficient learning of generalizable locomotion behaviors directly on the real robot. With hierarchical RL, the robot learned to coordinate policies at different levels to achieve more complex tasks. In the future, we plan to bring perception into the loop, so that robots can operate truly autonomously in the real world.
Follow the link to full article to learn more. Very exciting!
[Read More]