Engineers at the Swiss Center for Electronics and Microtechnology (CSEM) have developed an artificial intelligence (AI) system that uses advanced reinforcement learning — machine learning algorithms that use trial and error to optimize the AI’s behavior in relation to its environment. After being programmed with basic instructions, robots essentially train themselves by performing actions and learning from mistakes.
Reinforcement learning is based on a feedback and improvement loop. After every action taken, the agent (i.e., robot) receives feedback from its environment called a reward, which is a number that encodes the objective to be maximized by the agent. Since actions may have delayed consequences, the learning process aims to maximize the sum of rewards over time.
Reinforcement learning allows machines to learn to play strategy games such as chess, where one particular move may not have a noticeable immediate effect, but it may change the course of the game. AI is commonly trained using reinforcement learning, but the method presents challenges for real-world applications...
Would you like to access the complete CEP News Update?
No problem. You just have to complete the following steps.
You have completed 0 of 2 steps.
-
Log in
You must be logged in to view this content. Log in now.
-
AIChE Membership
You must be an AIChE member to view this article. Join now.
Copyright Permissions
Would you like to reuse content from CEP Magazine? It’s easy to request permission to reuse content. Simply click here to connect instantly to licensing services, where you can choose from a list of options regarding how you would like to reuse the desired content and complete the transaction.
