Self-organizing Neural Architecture for Reinforcement Learning
Self-organizing neural networks are typically associated with unsupervised learning. This paper presents a self-organizing neural architecture, known as TD-FALCON, that learns cognitive codes across multi-modal pattern spaces, involving states, actions, and rewards, and is capable of adapting and functioning in a dynamic environment with external evaluative feedback signals. We present a case study of TD-FALCON on a mine avoidance and navigation cognitive task, and illustrate its performance by comparing with a state-of-the-art reinforcement learning approach based on gradient descent backpropagation algorithm.
KeywordsReinforcement Learn Choice Function Autonomous Vehicle Adaptive Resonance Theory Greedy Policy
Unable to display preview. Download preview PDF.
- 2.Carpenter, G.A., Grossberg, S.: Adaptive Resonance Theory. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 87–90. MIT Press, Cambridge (2003)Google Scholar
- 3.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
- 5.Si, J., Barto, A.G., Powell, W.B., Wunsch, D. (eds.): Handbook of Learning and Approximate Dynamic Programming. Wiley-IEEE Press, Chichester (2004)Google Scholar