Lecture Notes on Partially Known MDPs

12/06/2021

∙

In these notes we will tackle the problem of finding optimal policies for Markov decision processes (MDPs) which are not fully known to us. Our intention is to slowly transition from an offline setting to an online (learning) setting. Namely, we are moving towards reinforcement learning.

READ FULL TEXT

Lecture Notes on Partially Known MDPs

An Efficient Solution to s-Rectangular Robust Markov Decision Processes

Online Learning in Adversarial MDPs: Is the Communicating Case Harder than Ergodic?

Online Learning for Unknown Partially Observable MDPs

Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning

Deep Reinforcement Learning for Backup Strategies against Adversaries

Transition Tensor Markov Decision Processes: Analyzing Shot Policies in Professional Basketball

Balancing detectability and performance of attacks on the control channel of Markov Decision Processes

Lecture Notes on Partially Known MDPs

Related Research

An Efficient Solution to s-Rectangular Robust Markov Decision Processes

Online Learning in Adversarial MDPs: Is the Communicating Case Harder than Ergodic?

Online Learning for Unknown Partially Observable MDPs

Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning

Deep Reinforcement Learning for Backup Strategies against Adversaries

Transition Tensor Markov Decision Processes: Analyzing Shot Policies in Professional Basketball

Balancing detectability and performance of attacks on the control channel of Markov Decision Processes