Neuroevolution strategies for episodic reinforcement learning.
Verena Heidrich-MeisnerChristian IgelPublished in: J. Algorithms (2009)
Keyphrases
- reinforcement learning
- function approximators
- artificial neural networks
- machine learning
- learning agents
- state space
- reinforcement learning algorithms
- optimal policy
- function approximation
- exploration strategy
- policy search
- controller design
- control strategies
- learning tasks
- monte carlo
- markov chain
- least squares
- hidden markov models
- multi agent
- website
- decision making