Stunt driving via policy search
Authors:
- 1 May 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4699-4704
Abstract
To explore or exploit? In this paper, we discuss the long-standing exploration-exploration dilemma in context of designing a learning controller for stunt-style driving with scarce samples. By making an efficient use of a single demonstration by an expert, our algorithm leverages our intuitive understanding of driving to extract a coarse dynamics model from the collected driving data, then formulate the policy search in a setting of gradient update with a specially designed cost function. Both theoretical and empirical results are detailed and discussed.Keywords
This publication has 7 references indexed in Scilit:
- Learning hover with scarce samples2012
- PRISCA: A policy search method for extreme trajectory following2011
- Driving Control Algorithm for Maneuverability, Lateral Stability, and Rollover Prevention of 4WD Electric Vehicles With Independently Driven Front and Rear WheelsIEEE Transactions on Vehicular Technology, 2011
- A probabilistic approach to mixed open-loop and closed-loop control, with application to extreme autonomous driving2010
- Nondifferentiable Optimization and Polynomial Problems1998
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992
- Maximum likelihood estimates of linear dynamic systemsAIAA Journal, 1965