Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

17

IJCAI
2003

favoriteEmaildiscussreport

188views Artificial Intelligence» more IJCAI 2003»

A Bayesian Approach to Imitation in Reinforcement Learning

13 years 5 months ago

A Bayesian Approach to Imitation in Reinforcement Learning

Download ijcai.org

In multiagent environments, forms of social learning such as teaching and imitation have been shown to aid the transfer of knowledge from experts to learners in reinforcement learning (RL). We recast the problem of imitation in a Bayesian framework. Our Bayesian imitation model allows a learner to smoothly pool prior knowledge, data obtained through interaction with the environment, and information inferred from observations of expert agent behaviors. Our model integrates well with recent Bayesian exploration techniques, and can be readily generalized to new settings.

Bob Price, Craig Boutilier

Real-time Traffic

Bayesian Framework | Bayesian Imitation Model | Expert Agent Behaviors | IJCAI 2003 | IJCAI 2007 |

claim paper

Related Content

» Active Imitation Learning

» Bayesian multitask inverse reinforcement learning

» Bayesian Reward Filtering

» Multitask reinforcement learning a hierarchical Bayesian approach

» Bayesian Imitation of Human Behavior in Interactive Computer Games

» Bayesian Policy Search for MultiAgent Role Discovery

» Coordination in multiagent reinforcement learning a Bayesian approach

» A bayesian reinforcement learning approach for customizing humanrobot interfaces

» Learning Object Affordances From SensoryMotor Coordination to Imitation

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2003
Where	IJCAI
Authors	Bob Price, Craig Boutilier

Comments (0)