Bayesian Reinforcement Learning

By Nikos A. Vlassis, Mohammad Ghavamzadeh, Shie Mannor, Pascal Poupart. 2010

96 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Information Systems, Reinforcement Learning, Probabilistic & Bayesian Methods

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

In Management Information Systems

In Reinforcement Learning

In Probabilistic & Bayesian Methods

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, methodology): “traditional RL community, proposing a wealth of exploration strategies including simple heuristics such as ε-greedy and Boltzmann exploration, Bayesian learning [22], [23], countbased methods with Probably Approximately Correct (PAC) guarantees [24], [25], as well as more expressive methods of intri”
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].”
Why is Posterior Sampling Better than Optimism for Reinforcement Learning? (2016, background): “For the most part, the literature on efficient RL is sharply divided between the frequentist and Bayesian perspective (Vlassis et al., 2012).”
EPOpt: Learning Robust Neural Network Policies Using Model Ensembles (2016, methodology): “L G ] 3 M ar 2 01 show in our experiments that such methods learn policies which are highly optimized for the specific models used in the simulator, but are brittle under model mismatch.”
A Physics-Based Model Prior for Object-Oriented MDPs (2014, methodology): “To motivate our approach, we first describe OO-LWR, an implementation of OO-MDP generalized to handle state-space dynamics.”
Bayesian Optimal Control of Smoothly Parameterized Systems (2015, methodology): “…e The reader interested in further algorithms for Bayesian reinforcement learning (including algorithms for inﬁnite state spaces) may consult the papers of Araya-L´opez et al. (2012), Vlassis et al. (2012) and Guez et al. (2013), which together give an excellent overview of the literature.”
Probabilistic machine learning and artificial intelligence (2015, background): “More broadly, important recent work takes a Bayesian approach to learning to control uncertain systems [73] (and see the review [74]).”
Scalable Planning and Learning for Multiagent POMDPs (2014, methodology): “learning (RL). BRL methods have become popular because they can provide a principled solution to this exploration/exploitation trade-off (Duff 2002; Engel, Mannor, and Meir 2005; Poupart et al. 2006; Vlassis et al. 2012). POMCP, discussed above, has been extended (Guez, Silver, and Dayan 2012) to so”