Recently, a team of researchers from Google Brain, Vector Institute and the University of Toronto showed that the entropy, information gain, and empowerment of reinforcement learning agents correlate strongly with a human behaviour similarity metric.  In the past few years, reinforcement learning has made several achievements in solving complex problems. From playing complex mind games…

The post Can RL Agents Behave More Human-Like Without Relying On Task Rewards? appeared first on Analytics India Magazine.