Deep Reinforcement Learning with Shallow Trees

Deep Reinforcement Learning with Shallow Trees: In this talk, I present Concept Network Reinforcement Learning (CNRL), developed at Bonsai. It is an industrially applicable approach to solving complex tasks using reinforcement learning, which facilitates problem decomposition, allows component reuse, and simplifies reward functions. Inspired by Sutton’s options framework, we introduce the notion of “Concept Networks” which are tree-like structures in which leaves are “sub-concepts” (sub-tasks), representing policies on a subset of state space. The parent (non-leaf) nodes are “Selectors”, containing policies on which sub-concept to choose from the child nodes, at each time during an episode. There will be a high-level overview on the reinforcement learning fundamentals at the beginning of the talk.

View the slides for this session