Improved neural fitted Q iteration applied to a novel computer gaming and learning benchmark.
Thomas GabelChristian LutzMartin A. RiedmillerPublished in: ADPRL (2011)
Keyphrases
- fitted q iteration
- reinforcement learning
- learning process
- neural network
- learning systems
- computer programming
- cognitive load
- learning algorithm
- online learning
- unsupervised learning
- supervised learning
- word processing
- data mining
- knowledge acquisition
- learning problems
- computer technology
- learning rules
- prior knowledge
- motor control
- spiking neural networks