Practical Issues in Temporal Difference Learning
Machine Learning
Temporal difference learning and TD-Gammon
Communications of the ACM
What are the computations of the cerebellum, the basal ganglia and the cerebral cortex?
Neural Networks - Special issue on organisation of computation in brain-like systems
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Self-Organizing Maps
Applications of the self-organising map to reinforcement learning
Neural Networks - New developments in self-organizing maps
Reinforcement learning with selective perception and hidden state
Reinforcement learning with selective perception and hidden state
Non-negative Matrix Factorization with Sparseness Constraints
The Journal of Machine Learning Research
A hybrid generative and predictive model of the motor cortex
Neural Networks
Learning tetris using the noisy cross-entropy method
Neural Computation
Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
Neural Computation
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
A sparse generative model of v1 simple cells with intrinsic plasticity
Neural Computation
Application of the self organizing maps for visual reinforcement learning of mobile robot
AIKED'08 Proceedings of the 7th WSEAS International Conference on Artificial intelligence, knowledge engineering and data bases
Closed-loop learning of visual control policies
Journal of Artificial Intelligence Research
Dynamics of cortical columns – self-organization of receptive fields
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Real-world reinforcement learning for autonomous humanoid robot charging in a home environment
TAROS'11 Proceedings of the 12th Annual conference on Towards autonomous robotic systems
Visual simulation of retinal images through microstructures
Microelectronic Engineering
Real-world reinforcement learning for autonomous humanoid robot docking
Robotics and Autonomous Systems
| Hi-index | 0.00 |
Only a subset of available sensory information is useful for decision making. Classical models of the brain's sensory system, such as generative models, consider all elements of the sensory stimuli. However, only the action-relevant components of stimuli need to reach the motor control and decision making structures in the brain. To learn these action-relevant stimuli, the part of the sensory system that feeds into a motor control circuit needs some kind of relevance feedback. We propose a simple network model consisting of a feature learning (sensory) layer that feeds into a reinforcement learning (action) layer. Feedback is established by the reinforcement learner's temporal difference (delta) term modulating an otherwise Hebbian-Iike learning rule of the feature learner. Under this influence, the feature learning network only learns the relevant features of the stimuli, i.e, those features on which goal-directed actions are to be based. With the input preprocessed in this manner, the reinforcement learner performs well in delayed reward tasks. The learning rule approximates an energy function's gradient descent. The model presents a link between reinforcement learning and unsupervised learning and may help to explain how the basal ganglia receive selective cortical input.