Goal Directed Adaptive Behavior in Second-Order Neural Networks: The MAXSON family of architectures

Abstract

The paper presents a neural network architecture (MAXSON) based on second-order connections that can learn a multiple goal approach/avoid task using reinforcement from the environment. It also enables an agent to learn vicariously, from the successes and failures of other agents. The paper shows that MAXSON can learn certain spatial navigation tasks much faster than traditional Q-learning, as well as learn goal directed behavior, increasing the agent's chances of long-term sur vival. The paper shows that an extension of MAXSON (V-MAXSON) enables agents to learn vicariously, and this improves the overall survivability of the agent population.