Affiliation:
1. U.S. Naval Academy, Annapolis, Maryland
2. University of California, Los Angeles
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.
Subject
Behavioral Neuroscience,Experimental and Cognitive Psychology
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献