Using Reward maximisation to achieve general artificial intelligence: Making machines behave like humans

Rewarding Reinforcement Learning makes machines behave like humans

Reward maximisation can be used to improve general artificial intelligence through reinforcement learning. Deep reinforcement learning algorithms should not rely on reward maximisation alone.

The identification of dual-purpose therapeutic target implicated in ageing and disease will prolong healthspan and delay age related health issues.

Source:
https://www.analyticsinsight.net/rewards-in-reinforcement-learning-make-machines-behave-like-humans/

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注