Reinforcement Learning(RL) is a type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences.
Reinforcement Learning is the best AI technique for Complex Industrial Systems. The widely published successes of DeepMinds AlphaZero and OpenAIs Dota bot have opened even more eyes to the almost magical capabilities of deep reinforcement learning agents.
Data Scientist with a strong background in Mathematics and Computer Science and experience in Data Analytics, Visualization, Data mining, Statistics and Machine Learning. Passionate about telling stories behind data to non-technical audiences. Frequent public speaker about Machine Learning, Deep Learning, Data Analytics and Artificial Intelligence at various National and International conferences.
Former Research Fellow at Indian Academy of Sciences, Bangalore and Indian Institute of Management, Ahmedabad. Responsible for driving product research at companies big or small. Worked with Red Hat, Inc, Adapty, Inc to develop their analytics engines/pipelines for automated reports and statistics. Led research at Institute of Nuclear Medicine and Allied Sciences - DRDO, Ministry of Defence, Govt. of India, Cognitive Science Lab. Worked at Facebook as a lead Research Engineer in the Connectivity Lab team to build the Offline Social Network.
Introduction to Reinforcement Learning
Markov Decision Processes
Supervised Learning and Imitation Learning
Model-Free Reinforcement Learning
Q-learning, Policy Gradients, Actor-Critic, etc.
Model-Based Reinforcement Learning (Monte Carlo Tree Search, etc.)
Topic to study in the future (Inverse Reinforcement Learning, Meta-Learning, etc)