Self-Organizing Maps
A self-organising network that grows when required
Neural Networks - New developments in self-organizing maps
Two steps reinforcement learning
International Journal of Intelligent Systems
Reinforcement learning in high-diameter, continuous environments
Reinforcement learning in high-diameter, continuous environments
Temporal Hebbian Self-Organizing Map for Sequences
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Sequential constant size compressors for reinforcement learning
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010)
IEEE Transactions on Autonomous Mental Development
Hi-index | 0.00 |
We present an architecture based on self-organizing maps for learning a sensory layer in a learning system. The architecture, temporal network for transitions (TNT), enjoys the freedoms of unsupervised learning, works on-line, in non-episodic environments, is computationally light, and scales well. TNT generates a predictive model of its internal representation of the world, making planning methods available for both the exploitation and exploration of the environment. Experiments demonstrate that TNT learns nice representations of classical reinforcement learning mazes of varying size (up to 20 × 20) under conditions of high-noise and stochastic actions.