Blog Posts
- A Ranking Game for Imitation Learning
- A new way to learn from expert demonstration and preferences in an unified framework.
- An Information Theory perspective on Thompson Sampling
- A simple way to derive interesting regret bounds for Thompson Sampling
- Improving RL with lookahead: Learning Off-Policy with Online Planning.
- A blog on how to effectively use lookahead to boost performance of Deep Reinforcement Learning methods.
- Robot Learning Spinning Up 2021
- A set of papers with review-style summary covering breadth of robot learning in perception and decision making.
- Opting for Higher Education
- Opinions on myths surrounding Higher Education and How to get there?
- Towards Safe Reinforcement Learning
- A brief overview to get starting in Safe RL
- Convex Hulls: Explained
- Algorithms for efficiently finding Convex Hull.
- Exploring Computational Geometry: Where to start?
- Getting started in Computational Geometry.