Material Detail

Binary Action Search for Learning Continuous-Action Control Policies

Binary Action Search for Learning Continuous-Action Control Policies

This video was recorded at 26th International Conference on Machine Learning (ICML), Montreal 2009. Reinforcement Learning methods for controlling stochastic processes typically assume a small and discrete action space. While continuous action spaces are quite common in real-world problems, the most common approach still employed in practice is coarse discretization of the action space. This paper presents a novel method, called Binary Action Search, for realizing continuous-action policies by searching efficiently the entire action range through increment and decrement modifications to the values of the action variables according to an internal binary policy defined over an augmented state space. The proposed approach essentially approximates any continuous action space to arbitrary... Show More


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.