Learning agents for uncertain environments (extended abstract)
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Algorithms for Inverse Reinforcement Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Apprenticeship learning via inverse reinforcement learning
ICML '04 Proceedings of the twenty-first international conference on Machine learning
ICML '06 Proceedings of the 23rd international conference on Machine learning
Apprenticeship learning using linear programming
Proceedings of the 25th international conference on Machine learning
Navigate like a cabbie: probabilistic reasoning from observed context-aware behavior
UbiComp '08 Proceedings of the 10th international conference on Ubiquitous computing
A survey of robot learning from demonstration
Robotics and Autonomous Systems
Maximum entropy inverse reinforcement learning
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Bayesian inverse reinforcement learning
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Map-matching for low-sampling-rate GPS trajectories
Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
A prsimonious model of mobile partitioned networks with clustering
COMSNETS'09 Proceedings of the First international conference on COMmunication Systems And NETworks
Learning behavior styles with inverse reinforcement learning
ACM SIGGRAPH 2010 papers
| Hi-index | 0.00 |
Most of the algorithms for inverse reinforcement learning (IRL) assume that the reward function is a linear function of the pre-defined state and action features. However, it is often difficult to manually specify the set of features that can make the true reward function representable as a linear function. We propose a Bayesian nonparametric approach to identifying useful composite features for learning the reward function. The composite features are assumed to be the logical conjunctions of the pre-defined atomic features so that we can represent the reward function as a linear function of the composite features. We empirically show that our approach is able to learn composite features that capture important aspects of the reward function on synthetic domains, and predict taxi drivers' behaviour with high accuracy on a real GPS trace dataset.