Traditional reinforcement learning methods require a function approx-imator (FA) for learning value functions in large or continuous state spaces. We describe a novel combination of CMAC-based FAs and adap-tive world models (WMs) estimating transition probabilities and rewards. Simple variants are tested in multiagent soccer environments where they outperform the evolutionary method PIPE which ...

The performance sensitivity of Albus' CMAC network was studied for the scenario in which faults are introduced into the adjustable weights after training has been accomplished. It was found that fault sensitivity was reduced with increased generalization when "loss of weight" faults were considered, but sensitivity was increased for "saturated weight" faults.

● Uses advanced encryption standard (AES) and its cipher-based message authentication code (CMAC) mode of operation for transmitter authentication ● 128, 192 or 256 Bit key sizes supported ● Uses sleep modes for low-power consumption ● Less than 30ms response time ● PC command-line tools for cryptographic key management ● Multiple transmitters supported ● Secure learning mechanism for introduci...