Ankur Narang; Senior Vice President – Technology & Decision Sciences at Yatra at Cypher2017- Part1/3

281 views · Published 10 October 2017 · 26:26 · Indexed 12 November 2026

Channel: AIM Network · 2017 · Science & Technology

Watch on YouTube

The Magic of Deep Reinforcement Learning
Deep Reinforcement Learning (DRL) is poised to revolutionize the field of AI and represents a step towards building autonomous systems with a higher level understanding.
It has a deep impact on multiple verticals including games, in particular, AlphaGo, Robotics, Natural Language Processing, Machine Translation, and Text Generation, Computer Vision, Business Management, Finance, Healthcare and Intelligent Transportation Systems. Magically, in some cases such as complex games (Go), its performance is way better than humans, while in other cases such as self-driven cars, it can work using video feeds to make complex driving decisions.

In this talk, we will look at the advances in AI techniques, that led to the development of Deep Reinforcement Learning. Applications of DRL to games, Robotics and finance will be presented as well. There are a lot of challenges ahead for DRL. Although DRL has already been combined with AI techniques, such as search and planning, a deeper integration with other traditional AI approaches promises benefits such as better sample complexity, generalisation and interpretability. A lot of progress needs to happen to realize the greater goal of general-purpose AI systems (AGI) that can interact with and learn from the world around them.
-----------------------------------------------------
Get in touch with us:

Website: www.analyticsindiamag.com
Contact: [email protected]
Facebook: https://www.facebook.com/AnalyticsIndiaMagazine/
Twitter: http://www.twitter.com/analyticsindiam
Linkedin: https://www.linkedin.com/company-beta/10283931/
Instagram: https://www.instagram.com/analyticsindiamagazine/

More from this channel