
Making Sense of Reinforcement Learning and Probabilistic Inference
Reinforcement learning (RL) combines a control problem with statistical ...
read it

Bayesian Reinforcement Learning: A Survey
Bayesian methods for machine learning have been widely investigated, yie...
read it

Optimal Reinforcement Learning for Gaussian Systems
The explorationexploitation tradeoff is among the central challenges o...
read it

Exploration versus exploitation in reinforcement learning: a stochastic control approach
We consider reinforcement learning (RL) in continuous time and study the...
read it

Approximate Robust Control of Uncertain Dynamical Systems
This work studies the design of safe control policies for largescale no...
read it

Bayesian Reinforcement Learning in Factored POMDPs
Bayesian approaches provide a principled solution to the explorationexp...
read it

A reinforcement learning approach to rare trajectory sampling
Very often when studying nonequilibrium systems one is interested in an...
read it
Dual Control for Approximate Bayesian Reinforcement Learning
Control of nonepisodic, finitehorizon dynamical systems with uncertain dynamics poses a tough and elementary case of the explorationexploitation tradeoff. Bayesian reinforcement learning, reasoning about the effect of actions and future observations, offers a principled solution, but is intractable. We review, then extend an old approximate approach from control theorywhere the problem is known as dual controlin the context of modern regression methods, specifically generalized linear regression. Experiments on simulated systems show that this framework offers a useful approximation to the intractable aspects of Bayesian RL, producing structured exploration strategies that differ from standard RL approaches. We provide simple examples for the use of this framework in (approximate) Gaussian process regression and feedforward neural networks for the control of exploration.
READ FULL TEXT
Comments
There are no comments yet.