Reward-predictive representations generalize across tasks in reinforcement learning.

ABSTRACT: In computer science, reinforcement learning is a powerful framework with which artificial agents can learn to maximize their performance for any given Markov decision process (MDP). Advances over the last decade, in combination with deep neural networks, have enjoyed performance advantages over humans in many difficult task settings. However, such frameworks perform far less favorably when evaluated in their ability to generalize or transfer representations across different tasks. Existing algorithms that facilitate transfer typically are limited to cases in which the transition function or the optimal policy is portable to new contexts, but achieving "deep transfer" characteristic of human behavior has been elusive. Such transfer typically requires discovery of abstractions that permit an

SUBMITTER: Lehnert L 

PROVIDER: S-EPMC7591094 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature