Bayesian models of human action understanding

Bayesian models of human action understanding (2006)

Cached

Download Links

[web.mit.edu]
[web.mit.edu]
[books.nips.cc]

Other Repositories/Bibliography

DBLP

by Chris L. Baker , Joshua B. Tenenbaum , Rebecca R. Saxe

Venue:	Advances in Neural Information Processing Systems 18
Citations:	13 - 3 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Bayesian models of human action understanding	SVM HeaderParse 0.2
AUTHOR NAME	Chris L. Baker	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Brain and Cognitive Sciences; Massachusetts Institute of Technology	SVM HeaderParse 0.2
AUTHOR NAME	Joshua B. Tenenbaum	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Brain and Cognitive Sciences; Massachusetts Institute of Technology	SVM HeaderParse 0.2
AUTHOR NAME	Rebecca R. Saxe	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Brain and Cognitive Sciences; Massachusetts Institute of Technology	SVM HeaderParse 0.2
ABSTRACT	We present a Bayesian framework for explaining how people reason about and predict the actions of an intentional agent, based on observing its behavior. Action-understanding is cast as a problem of inverting a probabilistic generative model, which assumes that agents tend to act rationally in order to achieve their goals given the constraints of their environment. Working in a simple sprite-world domain, we show how this model can be used to infer the goal of an agent and predict how the agent will act in novel situations or when environmental constraints change. The model provides a qualitative account of several kinds of inferences that preverbal infants have been shown to perform, and also fits quantitative predictions that adult observers make in a new experiment. 1	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	Advances in Neural Information Processing Systems 18	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	99--106	INFERENCE
VOLUME	18	INFERENCE
CITATIONS	14 found	ParsCit 1.0