Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage steps in the Q-function that are associated with accomplishing sub-tasks. Howeve...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-06
Main Authors: Patil, Vihang P, Hofmarcher, Markus, Marius-Constantin Dinu, Dorfer, Matthias, Blies, Patrick M, Brandstetter, Johannes, Arjona-Medina, Jose A, Hochreiter, Sepp
Format: Article
Language:English
Subjects:
Algorithms
Bioinformatics
Diamonds
Exploration
Machine learning
Rudders
Task complexity
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage steps in the Q-function that are associated with accomplishing sub-tasks. However, often only few episodes with high rewards are available as demonstrations since current exploration strategies cannot discover them in reasonable time. In this work, we introduce Align-RUDDER, which utilizes a profile model for reward redistribution that is obtained from multiple sequence alignment of demonstrations. Consequently, Align-RUDDER employs reward redistribution effectively and, thereby, drastically improves learning on few demonstrations. Align-RUDDER outperforms competitors on complex artificial tasks with delayed rewards and few demonstrations. On the Minecraft ObtainDiamond task, Align-RUDDER is able to mine a diamond, though not frequently. Code is available at https://github.com/ml-jku/align-rudder. YouTube: https://youtu.be/HO-_8ZUl-UY
ISSN:2331-8422