What Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances

Mohan Sridharan; Ben Meadows; Rocio Gomez

doi:10.1609/icaps.v27i1.13852

What Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances

Mohan Sridharan, Ben Meadows, Rocio Gomez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational representation and observations of action outcomes, are used to interactively and cumulatively (a) acquire knowledge of affordances of specific objects being operated upon by specific agents; and (b) generalize from these specific learned instances. The capabilities of this architecture are illustrated and evaluated in two simulated domains, a variant of the classic Blocks World domain, and a robot assisting humans in an office environment.

Original language	English
Title of host publication	Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017)
Publisher	AAAI Press
Pages	461-469
Number of pages	9
ISBN (Print)	978-1-57735-789-6
DOIs	https://doi.org/10.1609/icaps.v27i1.13852
Publication status	Published - 18 Jun 2017
Event	Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS) - Pittburgh, United States Duration: 18 Jun 2017 → 23 Jun 2017 Conference number: 27

Publication series

Name
ISSN (Print)	2334-0835
ISSN (Electronic)	2334-0843

Conference

Conference	Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS)
Abbreviated title	ICAPS 2017
Country/Territory	United States
City	Pittburgh
Period	18/06/17 → 23/06/17

Access to Document

10.1609/icaps.v27i1.13852Licence: All Rights Reserved

https://ojs.aaai.org/index.php/ICAPS/article/view/13852Licence: All Rights Reserved

Cite this

@inproceedings{927fa30d57aa4cdd856cb59d3d7a32b5,

title = "What Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances",

abstract = "This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational representation and observations of action outcomes, are used to interactively and cumulatively (a) acquire knowledge of affordances of specific objects being operated upon by specific agents; and (b) generalize from these specific learned instances. The capabilities of this architecture are illustrated and evaluated in two simulated domains, a variant of the classic Blocks World domain, and a robot assisting humans in an office environment.",

author = "Mohan Sridharan and Ben Meadows and Rocio Gomez",

year = "2017",

month = jun,

day = "18",

doi = "10.1609/icaps.v27i1.13852",

language = "English",

isbn = "978-1-57735-789-6",

publisher = "AAAI Press",

pages = "461--469",

booktitle = "Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017)",

note = "Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS), ICAPS 2017 ; Conference date: 18-06-2017 Through 23-06-2017",

}

Sridharan, M, Meadows, B & Gomez, R 2017, What Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances. in Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017). AAAI Press, pp. 461-469, Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS), Pittburgh, Pennsylvania, United States, 18/06/17. https://doi.org/10.1609/icaps.v27i1.13852

TY - GEN

T1 - What Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances

AU - Sridharan, Mohan

AU - Meadows, Ben

AU - Gomez, Rocio

N1 - Conference code: 27

PY - 2017/6/18

Y1 - 2017/6/18

N2 - This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational representation and observations of action outcomes, are used to interactively and cumulatively (a) acquire knowledge of affordances of specific objects being operated upon by specific agents; and (b) generalize from these specific learned instances. The capabilities of this architecture are illustrated and evaluated in two simulated domains, a variant of the classic Blocks World domain, and a robot assisting humans in an office environment.

AB - This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational representation and observations of action outcomes, are used to interactively and cumulatively (a) acquire knowledge of affordances of specific objects being operated upon by specific agents; and (b) generalize from these specific learned instances. The capabilities of this architecture are illustrated and evaluated in two simulated domains, a variant of the classic Blocks World domain, and a robot assisting humans in an office environment.

U2 - 10.1609/icaps.v27i1.13852

DO - 10.1609/icaps.v27i1.13852

M3 - Conference contribution

SN - 978-1-57735-789-6

SP - 461

EP - 469

BT - Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017)

PB - AAAI Press

T2 - Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS)

Y2 - 18 June 2017 through 23 June 2017

ER -

What Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this