Reinforcement Learning with Immediate Rewards and Linear Hypotheses.
Naoki AbeAlan W. BiermannPhilip M. LongPublished in: Algorithmica (2003)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- function approximation
- reinforcement learning algorithms
- learning algorithm
- function approximators
- machine learning
- model free
- learning problems
- learning process
- optimal policy
- dynamic programming
- linear systems
- temporal difference
- partially observable
- reinforcement learning methods
- reward shaping
- action selection
- optimal control
- dynamical systems
- search space
- multi agent
- bayesian networks
- genetic algorithm