BAM Learning of Nonlinearly Separable Tasks by Using an Asymmetrical Output Function and Reinforcement Learning.
Sylvain ChartierMounir BoukadoumMahmood AmiriPublished in: IEEE Trans. Neural Networks (2009)
Keyphrases
- reinforcement learning
- learning process
- multiple tasks
- supervised learning
- learning algorithm
- markov decision processes
- learning capabilities
- active learning
- online learning
- knowledge acquisition
- neural network
- model free
- robot control
- learning agent
- prior knowledge
- reinforcement learning methods
- evolutionary learning
- eligibility traces