Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

ICML 2018 • Rodrigo Toro Icarte • Toryn Klassen • Richard Valenzano • Sheila Mcilraith

In this paper we propose Reward Machines {—} a type of finite state machine that supports the specification of reward functions while exposing reward function structure to the learner and supporting decomposition. We then present Q-Learning for Reward Machines (QRM), an algorithm which appropriately decomposes the reward machine and uses off-policy q-learning to simultaneously learn subpolicies for the different components... (read more)

PDF Abstract

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Q-Learning	Off-Policy TD Control

METHOD

TYPE

Q-Learning

Off-Policy TD Control

Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Add Remove

Methods used in the Paper

Add Remove

Edit Social Preview

Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning Edit social preview

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit Add Remove

Methods used in the Paper Edit Add Remove

Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Add Remove

Methods used in the Paper

Add Remove