Reinforcement Learning in Continuous Time and Space
Neural Computation
A Computational Model of the Amygdala Nuclei's Role in Second Order Conditioning
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Fast Learning in an Actor-Critic Architecture with Reward and Punishment
Proceedings of the 2008 conference on Tenth Scandinavian Conference on Artificial Intelligence: SCAI 2008
Intrinsic Motivation Systems for Autonomous Mental Development
IEEE Transactions on Evolutionary Computation
Learning reactive and planning rules in a motivationally autonomousanimat
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Interactive Teaching for Vision-Based Mobile Robots: A Sensory-Motor Approach
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Hi-index | 0.00 |
Inspired by the emotional conditionings performed by the amygdala, we describe a simulated neural network able to learn the meaning of a previously neutral stimulation. A robot using this neural network can learn the conditioning of a non specific sensor activated by the experimentator and its internal state of pain or pleasure. This biologically inspired adaptative and natural way to interact with the robot is tested with a mobile robot learning navigation tasks in a real environment.