Partially Observable Markov Decision Processes

By Pascal Poupart. 2017

376 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Combining Kernel and Model Based Learning for HIV Therapy Selection (2017, background): “We summarise the core ideas for each of these steps below; for more details we refer the reader to [13, 14, 15].”
User-Centric Cell-Free Massive MIMO Networks: A Survey of Opportunities, Challenges and Solutions (2021, background): “Partially observable Markov decision process [165] [23] Discrete-time Markov model, Markov fluid model [60] Mobile edge computing (MEC) [166–168] Punctured scheduling [169] Protocols such as Precision Time Protocol (PTP) [160, 161]”
A Concise Introduction to Decentralized POMDPs (2016, background): “In order to represent such state uncertainty, a partially observable Markov decision process (POMDP) extends the MDP model by incorporating observations and their probability of occurrence conditional on the state of the environment [Kaelbling et al., 1998, Cassandra, 1998, Spaan, 2012].”
Reinforcement Learning of POMDPs using Spectral Methods (2016, background): “orizon (Papadimitriou and Tsitsiklis, 1987) and uncomputable for inﬁnite horizon ( Madani, 1998)). Many exact, approximate, and heuristic methods have been proposed to compute the optimal policy (see Spaan (2012) for a recent survey). An alternative approach is to consider memoryless policies which ”
On Q-learning Convergence for Non-Markov Decision Processes (2018, methodology): “A comprehensive survey of solution methods for POMDPs is provided by Murphy [ 2000 ] and more recently by Thrun et al. [ 2005 ] .”