We develop a new graphical representation for interactive partially observable Markov decision processes (I-POMDPs) that is significantly more transparent and semantically clear t...
Agents or agent teams deployed to assist humans often face the challenges of monitoring the state of key processes in their environment (including the state of their human users t...
Pradeep Varakantham, Rajiv T. Maheswaran, Milind T...
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
The Partially Observable Markov Decision Process has long been recognized as a rich framework for real-world planning and control problems, especially in robotics. However exact s...
Joelle Pineau, Geoffrey J. Gordon, Sebastian Thrun
We consider the average cost problem for partially observable Markov decision processes (POMDP) with finite state, observation, and control spaces. We prove that there exists an -...