This article reviews a very exciting ICLR 2019 paper: Adversarial Attacks on Graph Neural Networks via Meta Learning. This was originally written as part of a class assignment at UT dallas.
Relational RL has not made a lot of splashes in real-world because it is easier to write a planner than learn a relational RL agent. This might be about to change with the current achievements of the graph based relational reasoning approaches. This article summarizes my understanding of the pioneering work of Vinicius Zambaldi et al. (ICLR 2019) on Deep Relational RL.
Overview of Adam Santoro et al. (NeurIPS 2017).
My notes on Victor Garcia, Joan Bruna, ICLR 2018. Written as part of the Complex Networks course by Prof. Feng Chen.
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.
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.
My notes on Peter Veličković et al. ICLR 2018. Written as part of the Complex Networks course by Prof. Feng Chen.
My notes on Thomas N Kipf and Max Welling ICLR 2017. Written as part of the Complex Networks course by Prof. Feng Chen.