Object-focused advice in reinforcement learning

Samantha Krening, Brent Harrison, Karen M. Feigh, Charles Isbell, Andrea Thomaz

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations


In order for robots and intelligent agents to interact with and learn from people with no machine-learning expertise, robots should be able to learn from natural human instruction. Many human explanations consist of simple sentences without state information, yet most machine learning techniques that incorporate human guidance cannot use nonspecific explanations. This work aims to learn policies from a few sentences that aren't state specific. The proposed Object-focused advice links an object to an action, and allows a person to generalize over an object's state space. To evaluate this technique, agents were trained using Object-focused advice collected from participants in an experiment in the Mario Bros. domain. The results show that Object-focused advice performs better than when no advice is given, the agent can learn where to apply the advice in the state space, and the agent can recover from adversarial advice. Also, including warnings of what not do to in addition to advice of what actions to take improves performance.

Original languageEnglish
Title of host publicationAAMAS 2016 - Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems
Number of pages2
ISBN (Electronic)9781450342391
StatePublished - 2016
Event15th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016 - Singapore, Singapore
Duration: May 9 2016May 13 2016

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914


Conference15th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016

Bibliographical note

Publisher Copyright:
Copyright © 2016, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.


  • Advice
  • Human teachers
  • Reinforcement learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering


Dive into the research topics of 'Object-focused advice in reinforcement learning'. Together they form a unique fingerprint.

Cite this