Reinforcement Learning (RL) is an area of Machine Learning, which deals with designing fully autonomous agents that learn by interacting with their environments. Recently deep neural network (DNN) based techniques have become popular due to their ability to automatically learn rich feature representations from data. The use of DNNs within traditional reinforcement learning algorithms has accelerated progress in RL, given rise to the field of “Deep Reinforcement Learning” (DRL). Few of the success stories of DRL are achieving superhuman performance on “Atari Games” by just using the image pixels, beating the human world champion in the game of “Go”. In this talk, we will provide a gentle introduction to DRL and show how to train agents in OpenAI Gym environments.

Session Date and Time

Date: 22nd September 2020

Time: 4 PM - 5 PM

About the Speaker

Dinesh Khandelwal is a Research Scientist at IBM India Research Lab.  He has a Ph.D. in Machine Learning from IIT Delhi.  His primary research interests lie in the area of Deep Learning, Probabilistic Graphical Models, and Question Answering. He also holds a Master's degree in Machine Learning from IISc Bangalore. He has published in top venues for Computer Vision, Machine Learning, and NLP, including AAAI, ACL, CVIU, WACV, and PRL.

Note: Registrations close 24 hrs prior to the event and you will receive instructions to join 12-15 hours prior to commencement of the webinar.