Nature Communications (Nov 2019)

Optimizing agent behavior over long time scales by transporting value

  • Chia-Chun Hung,
  • Timothy Lillicrap,
  • Josh Abramson,
  • Yan Wu,
  • Mehdi Mirza,
  • Federico Carnevale,
  • Arun Ahuja,
  • Greg Wayne

DOI
https://doi.org/10.1038/s41467-019-13073-w
Journal volume & issue
Vol. 10, no. 1
pp. 1 – 12

Abstract

Read online

People are able to mentally time travel to distant memories and reflect on the consequences of those past events. Here, the authors show how a mechanism that connects learning from delayed rewards with memory retrieval can enable AI agents to discover links between past events to help decide better courses of action in the future.