Publications on Neuro-biological RL

Biased Random-Walk Learning: A Neurobiological Correlate to Trial-and-Error
Progress in Neural Networks (Postscript - 248KB) Abstract:
Neural network models offer a theoretical testbed for the study of learning at the network level. ...

A computational model of basal ganglia function with output selection and reinforcement learning, T.J. Sejnowski Society for Neuroscience Abstracts, 20:2 (1994 Abstract:
We propose a computational model of the basal ganglia based closely on known anatomy and physiology....

How the Brain Adjusts Synapses -- Maybe
Atomated Reasoning, Kluwer, NY (1991) (Hardcopy Only - ) Abstract:
chemotaxis algorithm neurobiological learning ...

E-mail: caironi@elet.polimi.it
Gradient-Based Reinforcement Learning: Learning Combinations of Control Policies
Technical Report 97.50, Dip. Elettronica e Informazione, Politecnico di Milano ( gzipped Postscript - 381 KB) Abstract:
This report presents two innovative model-based reinforcement learning algorithms for continuous st...

Using a time-delay actor-critic neural architecture with dopamine-like reinforcement signal for learning in autonomous robots
Emerging Neural Architectures based on Neuroscience, S. Wermter, J. Austin, D. Willshaw (Eds.), Springer-verlag, LNAI 2036, pp. 522-533. (PDF - 250 Kb) Abstract:
Neuroscientists have identified a neural substrate of prediction and reward in experiments wi...

Reinforcement learning predicts the site of plasticity for auditory remapping in the barn owl In: G. Tesauro, D. Touretzky and J. Alspector (Eds.) Advances in Neural Information Processing Systems 7, MIT Press, Cambridge, MA, 125-132 (1995). Abstract:
(no abstract available)...

E-mail: rivestfr@iro.umontreal.ca
Brain Inspired Reinforcement Learning
NIPS 2004 (NIPS 17) Abstract:
Successful application of reinforcement learning algorithms often involves considerable hand-craftin...

E-mail: mtr@cs.umass.edu
Robot weightlifting by direct policy search
IJCAI-01 (PDF - 815KB) Abstract:
This paper describes a method for structuring a robot motor learning task. By designing a suitably ...

Temporal sequence learning, prediction and control - A review of different models and their relation to biological mechanisms
Neural Computation, 17: 245-319 Abstract:
A review of RL in view of its relation to classical conditioning and the biophysics of the underlyin...

A Generic architecture for Adaptive Agents Based on Reinforcement Learning
Information Sciences Journal Abstract:
In this paper, we present MAABAC, a generic model for building adaptive agents: they learn new behav...