H
Henry Zhu
Researcher at University of California, Berkeley
Publications - 8
Citations - 1590
Henry Zhu is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Reinforcement learning & Instrumentation (computer programming). The author has an hindex of 7, co-authored 7 publications receiving 813 citations.
Papers
More filters
Posted Content
Soft Actor-Critic Algorithms and Applications
Tuomas Haarnoja,Aurick Zhou,Kristian Hartikainen,George Tucker,Sehoon Ha,Jie Tan,Vikash Kumar,Henry Zhu,Abhishek Gupta,Pieter Abbeel,Sergey Levine +10 more
TL;DR: Soft Actor-Critic (SAC), the recently introduced off-policy actor-critic algorithm based on the maximum entropy RL framework, achieves state-of-the-art performance, outperforming prior on-policy and off- policy methods in sample-efficiency and asymptotic performance.
Proceedings ArticleDOI
Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost
TL;DR: It is shown that contact-rich manipulation behavior with multi-fingered hands can be learned by directly training with model-free deep RL algorithms in the real world, with minimal additional assumption and without the aid of simulation, indicating that direct deep RL training in thereal world is a viable and practical alternative to simulation and model-based control.
Proceedings Article
The Ingredients of Real World Robotic Reinforcement Learning
Henry Zhu,Justin Yu,Abhishek Gupta,Dhruv Shah,Kristian Hartikainen,Avi Singh,Vikash Kumar,Sergey Levine +7 more
TL;DR: This work discusses the required elements of a robotic system that can continually and autonomously improve with data collected in the real world, and proposes a particular instantiation of such a system, and demonstrates the efficacy of this proposed system on dexterous robotic manipulation tasks in simulation and thereal world.
ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots
Michael Ahn,Henry Zhu,Kristian Hartikainen,Hugo Ponte,Abhishek Gupta,Sergey Levine,Vikash Kumar +6 more
TL;DR: This work proposes an extensible set of continuous control benchmark tasks for each robot, and provides benchmark scores on an initial set of tasks using a variety of learning-based methods, and shows that they can be replicated across copies of the robots located in different institutions.
Posted Content
The Ingredients of Real-World Robotic Reinforcement Learning
Henry Zhu,Justin Yu,Abhishek Gupta,Dhruv Shah,Kristian Hartikainen,Avi Singh,Vikash Kumar,Sergey Levine +7 more
TL;DR: In this paper, the authors discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world, using dexterous manipulation as their case study.