Reinforcement Learning, Spike-Time-Dependent Plasticity, and the BCM Rule.
Dorit BarasRon MeirPublished in: Neural Comput. (2007)
Keyphrases
- reinforcement learning
- spike trains
- function approximation
- learning mechanism
- model free
- reinforcement learning algorithms
- temporal difference
- state space
- markov decision processes
- rule sets
- machine learning
- biologically inspired
- feed forward
- classification rules
- optimal policy
- learning process
- learning algorithm
- spiking neurons
- hidden markov models
- travel time
- rule induction
- association rules
- multi agent systems
- rule discovery
- biologically plausible
- reinforcement learning methods
- data sets