Timezone: »

Constrained Variational Policy Optimization for Safe Reinforcement Learning
Zuxin Liu · Zhepeng Cen · Vladislav Isenbaev · Wei Liu · Steven Wu · Bo Li · Ding Zhao

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #909

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.Previous primal-dual style approaches suffer from instability issues and lack optimality guarantees. This paper overcomes the issues from the perspective of probabilistic inference. We introduce a novel Expectation-Maximization approach to naturally incorporate constraints during the policy learning: 1) a provable optimal non-parametric variational distribution could be computed in closed form after a convex optimization (E-step); 2) the policy parameter is improved within the trust region based on the optimal variational distribution (M-step).The proposed algorithm decomposes the safe RL problem into a convex optimization phase and a supervised learning phase, which yields a more stable training performance.A wide range of experiments on continuous robotic tasks shows that the proposed method achieves significantly better constraint satisfaction performance and better sample efficiency than baselines.The code is available at https://github.com/liuzuxin/cvpo-safe-rl.

Author Information

Zuxin Liu (Carnegie Mellon University)
Zhepeng Cen (Carnegie Mellon University)
Vladislav Isenbaev (Nuro Inc.)
Wei Liu (Nuro Inc.)
Steven Wu (Carnegie Mellon University)
Bo Li (UIUC)
Bo Li

Dr. Bo Li is an assistant professor in the Department of Computer Science at the University of Illinois at Urbana–Champaign. She is the recipient of the IJCAI Computers and Thought Award, Alfred P. Sloan Research Fellowship, AI’s 10 to Watch, NSF CAREER Award, MIT Technology Review TR-35 Award, Dean's Award for Excellence in Research, C.W. Gear Outstanding Junior Faculty Award, Intel Rising Star award, Symantec Research Labs Fellowship, Rising Star Award, Research Awards from Tech companies such as Amazon, Facebook, Intel, IBM, and eBay, and best paper awards at several top machine learning and security conferences. Her research focuses on both theoretical and practical aspects of trustworthy machine learning, which is at the intersection of machine learning, security, privacy, and game theory. She has designed several scalable frameworks for trustworthy machine learning and privacy-preserving data publishing. Her work has been featured by major publications and media outlets such as Nature, Wired, Fortune, and New York Times.

Ding Zhao (Carnegie Mellon University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors