Bayesian reinforcement learning: a survey
From MaRDI portal
Abstract: Bayesian methods for machine learning have been widely investigated, yielding principled methods for incorporating prior information into inference algorithms. In this survey, we provide an in-depth review of the role of Bayesian methods for the reinforcement learning (RL) paradigm. The major incentives for incorporating Bayesian reasoning in RL are: 1) it provides an elegant approach to action-selection (exploration/exploitation) as a function of the uncertainty in learning; and 2) it provides a machinery to incorporate prior knowledge into the algorithms. We first discuss models and methods for Bayesian inference in the simple single-step Bandit model. We then review the extensive recent literature on Bayesian methods for model-based RL, where prior information can be expressed on the parameters of the Markov model. We also present Bayesian methods for model-free RL, where priors are expressed over the value function or policy class. The objective of the paper is to provide a comprehensive survey on Bayesian RL algorithms and their theoretical and empirical properties.
Recommendations
- Dual control for approximate Bayesian reinforcement learning
- A Bayesian approach for learning and planning in partially observable Markov decision processes
- Bayesian Reinforcement Learning with Exploration
- Transfer learning for reinforcement learning domains: a survey
- Reinforcement learning theory, algorithms and its application
Cited in
(31)- A Bayesian perspective of statistical machine learning for big data
- Nonparametric additive value functions: interpretable reinforcement learning with an application to surgical recovery
- Optimal Treatment Regimes: A Review and Empirical Comparison
- Bayesian Reinforcement Learning with Exploration
- Reinforcement Learning, Bit by Bit
- Learning and planning in partially observable environments without prior domain knowledge
- A Bayesian reinforcement learning approach in Markov games for computing near-optimal policies
- scientific article; zbMATH DE number 7415125 (Why is no real title available?)
- Embedding active learning in batch-to-batch optimization using reinforcement learning
- A model for system uncertainty in reinforcement learning
- Finding the optimal exploration-exploitation trade-off online through Bayesian risk estimation and minimization
- Reinforcement learning, sequential Monte Carlo and the EM algorithm
- A new algorithm for the LQR problem with partially unknown dynamics
- Planning in artificial intelligence
- Reinforcement learning
- A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
- Constrained multiagent Markov decision processes: a taxonomy of problems and algorithms
- Active Inference: Demystified and Compared
- Personalized optimization with user's feedback
- Inverse reinforcement learning via nonparametric spatio-temporal subgoal modeling
- Bayesian policy gradient and actor-critic algorithms
- Learning reward machines: a study in partially observable reinforcement learning
- Statistical field theory for Markov decision processes under uncertainty
- scientific article; zbMATH DE number 7626804 (Why is no real title available?)
- Model-based Reinforcement Learning: A Survey
- Sophisticated inference
- Reward Maximization Through Discrete Active Inference
- On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability
- Robust moving target defense against unknown attacks: a meta-reinforcement learning approach
- Modern Bayesian experimental design
- Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning
This page was built for publication: Bayesian reinforcement learning: a survey
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2809805)
