Search Results for author: Thomas Wheeler

Found 1 papers, 0 papers with code

Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems

no code implementations11 Feb 2020 Sushmita Bhattacharya, Sahil Badyal, Thomas Wheeler, Stephanie Gil, Dimitri Bertsekas

In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, and partial state observations.

Cannot find the paper you are looking for? You can Submit a new open access paper.