A Bayesian Approach for Learning and Planning in Partially Observable Markov Decision Processes

By Stéphane Ross, Joelle Pineau, Brahim Chaib-draa, Pierre Kreitmann. 2011

155 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): “Sampling a model given this Dirichlet prior is relatively straightforward; we only need to keep track of the number of times we believe a physiological state may have been visited [15]: T (s′|s, a) = φs,s′ ∑ s′′∈S φ a s,s′′ Ω(o|s, a) = ψ s,o ∑ o′∈Ω φ a s,o′ .”
Deep Variational Reinforcement Learning for POMDPs (2018, methodology): “, 2016), a Bayesian approach (Ross et al., 2011; Katt et al., 2017), or nonparametrically (Doshi-Velez et al.”
A probabilistic graphical model foundation for enabling predictive digital twins at scale (2020, background): “Recent approaches typically restrict focus to a subset of the belief space [24], or adopt Monte Carlo sampling approaches [25] and learning algorithms [26, 27, 28].”
Bayesian Reinforcement Learning in Factored POMDPs (2018, methodology): “The Bayes-Adaptive POMDP (BA-POMDP) [39] is a POMDP in which the counts χ are part of the hidden state space.”
Reinforcement learning for control: Performance, stability, and deep approximators (2018, unknown): “Like in RL, the exploitation-exploration issue can be addressed using e.g. Bayesian RL ideas (Ross et al., 2011).”
Convex Optimization: Algorithms and Complexity (2015, unknown): “We can extend the BAMDP model to capture uncertainty over the parameters of a POMDP (as defined in §2.3) by introducing the BayesAdaptive POMDP (BAPOMDP) model [Ross et al., 2008a, 2011].”
From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning (2014, methodology): “However the planning problem of the BAPOMDP is more challenging because the branching factor now scales with the number of states of the original POMDP (see [Ross et al., 2011]).”
Scalable Planning and Learning for Multiagent POMDPs (2014, methodology): “Moreover, the method has demonstrated good performance in large domains with a limited number of simulations.”