Flexible Option Learning

By Martin Klissarov, Doina Precup. 2021

36 citations recorded by the source corpus.

Temporal abstraction in reinforcement learning (RL), offers the promise of improving generalization and knowledge transfer in complex environments, by propagating information more efficiently over time. Although option learning was initially formulated in a way that allows updating many options simultaneously, using off-policy, intra-option learning (Sutton, Precup&Singh, 1999), many of the recent hierarchical reinforcement learning approaches only update a single option at a time: the option currently executing. We revisit and extend intra-option learning in the context of deep reinforcement learning, in order to enable updating all options consistent with current primitive action choices, without introducing any additional estimates. Our method can therefore be naturally adopted in most hierarchical RL frameworks. When we combine our approach with the option-critic algorithm for option discovery, we obtain significant improvements in performance and data-efficiency across a wide variety of domains.

Subfields: Management Science and Operations Research, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

  1. Doina Precup
  2. Irina Rish
  3. Khimya Khetarpal
  4. Matthew Riemer
  5. Sergey Levine
  6. Ofir Nachum
  7. Aviral Kumar
  8. George Tucker

In Ocean Engineering

  1. Doina Precup

Citations in the corpus