An information-theoretic analysis of return maximization in reinforcement learning.
Kazunori IwataPublished in: Neural Networks (2011)
Keyphrases
- reinforcement learning
- state space
- markov decision processes
- reinforcement learning algorithms
- learning algorithm
- objective function
- machine learning
- function approximation
- control problems
- learning process
- model free
- robotic control
- transfer learning
- transition model
- partially observable
- temporal difference
- optimal policy
- direct policy search
- relational reinforcement learning
- perceptual aliasing
- policy search
- learning problems
- evolutionary learning
- learning tasks
- monte carlo
- supervised learning
- genetic algorithm