Timezone: »

Control Regularization for Reduced Variance Reinforcement Learning
Richard Cheng · Abhinav Verma · Gabor Orosz · Swarat Chaudhuri · Yisong Yue · Joel Burdick

Wed Jun 12 02:20 PM -- 02:25 PM (PDT) @ Hall B

Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization approach to augmenting model-free RL. In particular, we regularize the behavior of the deep policy to be similar to a control prior, i.e., we regularize in function space. We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off. When the prior policy has control-theoretic stability guarantees, we further show that this regularization approximately preserves those stability guarantees throughout learning. We validate our approach empirically on a wide range of settings, and demonstrate significantly reduced variance, guaranteed dynamic stability, and more efficient learning than deep RL alone.

Author Information

Richard Cheng (California Institute of Technology)
Abhinav Verma (Rice University)
Gabor Orosz (University of Michigan)
Swarat Chaudhuri (Rice University)
Yisong Yue (Caltech)

Yisong Yue is an assistant professor in the Computing and Mathematical Sciences Department at the California Institute of Technology. He was previously a research scientist at Disney Research. Before that, he was a postdoctoral researcher in the Machine Learning Department and the iLab at Carnegie Mellon University. He received a Ph.D. from Cornell University and a B.S. from the University of Illinois at Urbana-Champaign. Yisong's research interests lie primarily in the theory and application of statistical machine learning. He is particularly interested in developing novel methods for interactive machine learning and structured prediction. In the past, his research has been applied to information retrieval, recommender systems, text classification, learning from rich user interfaces, analyzing implicit human feedback, data-driven animation, behavior analysis, sports analytics, policy learning in robotics, and adaptive planning & allocation problems.

Joel Burdick (Caltech)

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

More from the Same Authors