Inference of Strategic Behavior based on Incomplete Observation Data

Antti Kangasrääsiö; Samuel Kaski

Inference of Strategic Behavior based on Incomplete Observation Data

Antti Kangasrääsiö, Samuel Kaski

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

89 Downloads (Pure)

Abstract

Inferring the goals, preferences and restrictions of strategically behaving agents is a common goal in many situations, and an important requirement for enabling computer systems to better model and understand human users.
Inverse reinforcement learning (IRL) is one method for performing this kind of inference based on observations of the agent's behavior.
However, traditional IRL methods are only applicable when the observations are in the form of state-action paths -- an assumption which does not hold in many real-world modelling settings.
This paper demonstrates that inference is possible even with an arbitrary observation noise model.

Original language	English
Title of host publication	NIPS17 Workshop: Learning in the Presence of Strategic Behavior
Publisher	CARNEGIE MELLON UNIVERSITY
Number of pages	4
Publication status	Published - 8 Dec 2017
MoE publication type	D3 Professional conference proceedings
Event	IEEE Conference on Neural Information Processing Systems - Long Beach, United States Duration: 4 Dec 2017 → 9 Dec 2017 Conference number: 31

Conference

Conference	IEEE Conference on Neural Information Processing Systems
Abbreviated title	NIPS
Country/Territory	United States
City	Long Beach
Period	04/12/2017 → 09/12/2017

Keywords

Inverse reinforcement learning
Bayesian Inference
Approximate Bayesian computation
Monte Carlo simulation

Access to Document

PreprintAccepted author manuscript, 382 KB

OpenUrl availability

Full text

Cite this

@inproceedings{453d68b453fd4f53800dbffaa4d4f994,

title = "Inference of Strategic Behavior based on Incomplete Observation Data",

abstract = "Inferring the goals, preferences and restrictions of strategically behaving agents is a common goal in many situations, and an important requirement for enabling computer systems to better model and understand human users.Inverse reinforcement learning (IRL) is one method for performing this kind of inference based on observations of the agent's behavior.However, traditional IRL methods are only applicable when the observations are in the form of state-action paths -- an assumption which does not hold in many real-world modelling settings.This paper demonstrates that inference is possible even with an arbitrary observation noise model.",

keywords = "Inverse reinforcement learning, Bayesian Inference, Approximate Bayesian computation, Monte Carlo simulation",

author = "Antti Kangasr{\"a}{\"a}si{\"o} and Samuel Kaski",

year = "2017",

month = dec,

day = "8",

language = "English",

booktitle = "NIPS17 Workshop: Learning in the Presence of Strategic Behavior",

publisher = "CARNEGIE MELLON UNIVERSITY",

address = "United States",

note = "IEEE Conference on Neural Information Processing Systems, NIPS ; Conference date: 04-12-2017 Through 09-12-2017",

}

TY - GEN

T1 - Inference of Strategic Behavior based on Incomplete Observation Data

AU - Kangasrääsiö, Antti

AU - Kaski, Samuel

N1 - Conference code: 31

PY - 2017/12/8

Y1 - 2017/12/8

N2 - Inferring the goals, preferences and restrictions of strategically behaving agents is a common goal in many situations, and an important requirement for enabling computer systems to better model and understand human users.Inverse reinforcement learning (IRL) is one method for performing this kind of inference based on observations of the agent's behavior.However, traditional IRL methods are only applicable when the observations are in the form of state-action paths -- an assumption which does not hold in many real-world modelling settings.This paper demonstrates that inference is possible even with an arbitrary observation noise model.

AB - Inferring the goals, preferences and restrictions of strategically behaving agents is a common goal in many situations, and an important requirement for enabling computer systems to better model and understand human users.Inverse reinforcement learning (IRL) is one method for performing this kind of inference based on observations of the agent's behavior.However, traditional IRL methods are only applicable when the observations are in the form of state-action paths -- an assumption which does not hold in many real-world modelling settings.This paper demonstrates that inference is possible even with an arbitrary observation noise model.

KW - Inverse reinforcement learning

KW - Bayesian Inference

KW - Approximate Bayesian computation

KW - Monte Carlo simulation

UR - https://www.cs.cmu.edu/~nhaghtal/mlstrat/

M3 - Conference contribution

BT - NIPS17 Workshop: Learning in the Presence of Strategic Behavior

PB - CARNEGIE MELLON UNIVERSITY

T2 - IEEE Conference on Neural Information Processing Systems

Y2 - 4 December 2017 through 9 December 2017

ER -

Inference of Strategic Behavior based on Incomplete Observation Data

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Interactive machine learning from multiple biodata sources

Interactive machine learning from multiple biodata sources

Science-IT

Cite this

Inference of Strategic Behavior based on Incomplete Observation Data

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Projects

Interactive machine learning from multiple biodata sources

Interactive machine learning from multiple biodata sources

Equipment

Science-IT

Cite this