Sciweavers

595 search results - page 81 / 119
» Predictive State Representations with State Space Partitioni...
Sort
View
111
Voted
AIPS
1998
15 years 5 months ago
Making Forward Chaining Relevant
Planning by forward chaining through the world space has long been dismissed as being "obviously" infeasible. Nevertheless, this approach to planning has many advantages...
Fahiem Bacchus, Yee Whye Teh
141
Voted
JMLR
2010
137views more  JMLR 2010»
14 years 10 months ago
Importance Sampling for Continuous Time Bayesian Networks
A continuous time Bayesian network (CTBN) uses a structured representation to describe a dynamic system with a finite number of states which evolves in continuous time. Exact infe...
Yu Fan, Jing Xu, Christian R. Shelton
137
Voted
ICRA
2009
IEEE
132views Robotics» more  ICRA 2009»
15 years 10 months ago
Smoothed Sarsa: Reinforcement learning for robot delivery tasks
— Our goal in this work is to make high level decisions for mobile robots. In particular, given a queue of prioritized object delivery tasks, we wish to find a sequence of actio...
Deepak Ramachandran, Rakesh Gupta
118
Voted
ICRA
2007
IEEE
128views Robotics» more  ICRA 2007»
15 years 10 months ago
Adaptive Play Q-Learning with Initial Heuristic Approximation
Abstract— The problem of an effective coordination of multiple autonomous robots is one of the most important tasks of the modern robotics. In turn, it is well known that the lea...
Andriy Burkov, Brahim Chaib-draa
127
Voted
ECML
2007
Springer
15 years 9 months ago
Imitation Learning Using Graphical Models
Imitation-based learning is a general mechanism for rapid acquisition of new behaviors in autonomous agents and robots. In this paper, we propose a new approach to learning by imit...
Deepak Verma, Rajesh P. N. Rao