Learning Reward Machines for Partially Observable Reinforcement Learning

Rodrigo Toro Icarte
Rodrigo Toro Icarte
Ethan Waldie
Ethan Waldie
Toryn Klassen
Toryn Klassen
Rick Valenzano
Rick Valenzano
Margarita Castro
Margarita Castro

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 15497-15508, 2019.

Cited by: 5|Bibtex|Views10|
EI
Keywords:
reinforcement learning

Abstract:

Reward Machines (RMs) provide a structured, automata-based representation of a reward function that enables a Reinforcement Learning (RL) agent to decompose an RL problem into structured subproblems that can be efficiently learned via off-policy learning. Here we show that RMs can be learned from experience, instead of being specified by ...More

Code:

Data:

Your rating :
0

 

Tags
Comments