Nonlinear Sciences – Adaptation and Self-Organizing Systems
Scientific paper
2011-04-19
Nonlinear Sciences
Adaptation and Self-Organizing Systems
21 pages, 18 figures. Extended version with new material. References and discussion of literature added. New results e.g. on s
Scientific paper
We propose a model of a learning agent whose interaction with the environment is governed by a simulation-based projection, which allows the agent to project itself into future situations before it takes real action. Projective simulation is based on a random walk through a network of clips, which are elementary patches of episodic memory. The network of clips changes dynamically, both due to new perceptual input and due to certain compositional principles of the simulation process. During simulation, the clips are screened for specific features which trigger factual action of the agent. The scheme is different from other, computational, notions of simulation, and it provides a new element in an embodied cognitive science approach to intelligent action and learning. Our model provides a natural route for generalization to quantum-mechanical operation and connects the fields of reinforcement learning and quantum computation.
Briegel Hans J.
las Cuevas Gemma de
No associations
LandOfFree
Projective simulation for classical and quantum learning agents does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Projective simulation for classical and quantum learning agents, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Projective simulation for classical and quantum learning agents will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-183464