We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....
- The effectiveness of stochastic power management relies on the accurate system and workload model and effective policy optimization. Workload modeling is a machine learning proce...
— An important problem in robotics is planning and selecting actions for goal-directed behavior in noisy uncertain environments. The problem is typically addressed within the fra...
We present a major improvement to the incremental pruning algorithm for solving partially observable Markov decision processes. Our technique targets the cross-sum step of the dyn...
Partially Observable Markov Decision Processes have been studied widely as a model for decision making under uncertainty, and a number of methods have been developed to find the s...