harsha kokel
Blog posts

Relational Reinforcement Learning
My notes on Džeroski, Sašo, Luc De Raedt, and Kurt Driessens, Machine Learning 2001

FewShot Learning with GNN
My notes on Victor Garcia, Joan Bruna, ICLR 2018. Written as part of the Complex Networks course by Prof. Feng Chen.

Relational Inductive Bias
There is a recent surge in papers which are using Relational Inductive Bias with Deep Reinforcement Learning. So here is my investigation on what is it and how is this connected to the inductive biases used in Logic.

ModelAgnostic MetaLearning
My notes on Chelsea Finn, Pieter Abbeel, Sergey Levine, ICML 2017. Written as part of the Complex Networks course by Prof. Feng Chen.

Hindsight Experience Replay
My notes on Marcin Andrychowicz et al. NeurIPS 2017.

Logical Program Policies
My notes on Tom Silver, Kelsey R. Allen, Alex K. Lew, Leslie Kaelbling, and Josh Tenenbaum, AAAI 2020.

Understanding Attention and Generalization in Graph Neural Networks
My notes on Boris Knyazev, Graham W. Taylor, and Mohamed R. Amer, NeurIPS 2019. Written as part of the Complex Networks course by Prof. Feng Chen.

Graph Attention Networks
My notes on Peter Veličković et al. ICLR 2018. Written as part of the Complex Networks course by Prof. Feng Chen.

Graph Convolutional Networks
My notes on Thomas N Kipf and Max Welling ICLR 2017. Written as part of the Complex Networks course by Prof. Feng Chen.

Fitted Q and Batch Reinforcement Learning
Some pointers on Batch Reinforcement Learning and Fitted Q. These were gathered while working on an RL for healthcare project, as part of Advanced RL course by Prof. Sriraam Natarajan.