Markov Decision Process
Markov Decision Processes (MDPs) are mathematical frameworks for modeling sequential decision-making problems under uncertainty, aiming to find optimal policies that maximize cumulative rewards. Current research emphasizes efficient algorithms for solving MDPs, particularly in complex settings like partially observable MDPs (POMDPs) and constrained MDPs (CMDPs), often employing techniques like policy gradient methods, Q-learning, and active inference. These advancements are crucial for improving the design and analysis of autonomous systems, robotics, and other applications requiring intelligent decision-making in dynamic environments, with a growing focus on addressing issues of safety, robustness, and sample efficiency.
Papers
Computing Approximated Fixpoints via Dampened Mann Iteration
Paolo Baldan, Sebastian Gurke, Barbara König, Tommaso Padoan, Florian Wittbold
Separation Assurance in Urban Air Mobility Systems using Shared Scheduling Protocols
Surya Murthy, Tyler Ingebrand, Sophia Smith, Ufuk Topcu, Peng Wei, Natasha Neogi
Markov Decision Processes for Satellite Maneuver Planning and Collision Avoidance
William Kuhl, Jun Wang, Duncan Eddy, Mykel Kochenderfer
A New Interpretation of the Certainty-Equivalence Approach for PAC Reinforcement Learning with a Generative Model
Shivaram Kalyanakrishnan, Sheel Shah, Santhosh Kumar Guguloth