Bayesian Reinforcement Learning
(Redirected from Bayes Adaptive Markov Decision Processes)
Jump to navigation
Jump to search
A Bayesian Reinforcement Learning is Reinforcement Learning Task based on a Bayesian Learning Algorithm.
- AKA: Adaptive Control Processes, Bayes Adaptive Markov Decision Processes, Dual control, Optimal Learning.
- See: Active Learning; Markov Decision Processes; Reinforcement Learning.
References
- (Poupart, 2017) ⇒ Poupart P. (2017) Bayesian Reinforcement Learning. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA
- QUOTE: Bayesian reinforcement learning refers to reinforcement learning modeled as a Bayesian learning problem (see Bayesian Methods). More specifically, following Bayesian learning theory, reinforcement learning is performed by computing a posterior distribution on the unknowns (e.g., any combination of the transition probabilities, reward probabilities, value function, value gradient, or policy) based on the evidence received (e.g., history of past state–action pairs).