Extending cortical-basal inspired reinforcement learning model with success-failure experience.
Shoubhik DebnathJohn NassourPublished in: ICDL-EPIROB (2014)
Keyphrases
- artificial neural networks
- reinforcement learning
- computational model
- high level
- theoretical framework
- genetic algorithm
- machine learning
- experimental data
- mathematical model
- cost function
- probabilistic model
- probability distribution
- model based diagnosis
- state space
- dynamic programming
- e learning
- information systems
- social networks