DRL has been used to optimize optimize chemical reactions, outperforming an existing state-of-the-art algorithm used to conduct the same experiment. A reinforcement learning agent successfully optimized a sequential chemical reaction, predicting at every stage of the experiment which action would generate the most desirable chemical reaction.

University of Michigan - Ann Arbor

Examples of DRL use in real-world environments can be found in:

1) Robotics

2) Healthcare Applications

3) Chemistry

Applications of Deep Reinforcement Learning

https://missinglink.ai/guides/neural-network-concepts/complete-guide-deep-reinforcement-learning-concepts-process-real-world-applications/

Complete Guide to Deep Reinforcement Learning: Concepts, Process, and Real World Applications

Using DRL in robotics has become easier since Google published its Soft Actor Critic algorithm. This algorithm helps robots use reinforcement learning to learn real-world tasks without the need for huge datasets or a large number of attempts, and while safeguarding the robot from taking actions that could cause it damage. For example, the algorithm has thus far taken a few hours in successfully training an insect robot to walk and a robot hand to carry out simple tasks.

DRL in Robotics

DRL can be employed in healthcare due to the large amount of historical medical data to evaluate the success of treatments for current patients. For example, DRL is used to predict drug doses for sepsis patients, for finding optimal dose cycles for chemotherapy, and selecting dynamic treatment regimes combining hundreds of possible medications based on medical registry data.

Learn Before

Related