Published inAnalytics VidhyaReflections on ICLR2020Lessons from attending my first ever virtual conferenceMay 1, 20203May 1, 20203
Published inAnalytics VidhyaRL Series#3: To explore or not to explore, that is the questionThe exploration-exploitation dilemma in RLApr 8, 20201Apr 8, 20201
RL Series #2: Learning with Deep Q Network (DQN)Exploring the theory and code behind DQNMar 23, 2020Mar 23, 2020
RL Series #1: Introduction to Reinforcement LearningBasic concepts and setting up for the seriesMar 18, 2020Mar 18, 2020
Published inDataDrivenInvestorUsing Human Intervention for Safer RLSummary of the paper by William Saunders et. al., titled “Trial without Error”Oct 27, 2019Oct 27, 2019
How to ensure that our AI systems are fair?Key insights from Timnit Gebru’s talk on Fairness in AI at MLSS 2019, LondonJul 25, 2019Jul 25, 2019