Reinforcement Learning with Pattern-based Rewards.
James F. PetersChristopher J. HenrySheela RamannaPublished in: Computational Intelligence (2005)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- state space
- reward function
- reinforcement learning algorithms
- learning algorithm
- learning process
- reward shaping
- temporal difference
- learning problems
- optimal policy
- optimal control
- model free
- markov decision process
- dynamic environments
- supervised learning
- multi agent
- machine learning
- complex domains
- policy search
- control policy
- learning agents
- reinforcement learning methods
- data sets
- transfer learning
- hidden state
- function approximators
- monte carlo