Research

Reinforcement Learning

It is all about learning from mistakes! Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward.

Below are some resources you can follow and study to get started within this exciting area.

Decision-Theoretic Planning

The area officially called decision-theoretic planning can also be considered as planning under uncertainty or decision-making under uncertainty. One key part of this research area is how to model the uncertainties which could interfere with predictability and sensing.

Below are some useful materials for you to read and you can also click the picture to read a more classical book about planning.

Multi-Agent Systems

The research area now known as multi-agent systems (MAS) was initially called "distributed AI" (DAI). MAS research is to study systems that consist of a group of agents that can potentially interact with each other.

Here is a handful of resources that may be helpful to you at the beginning of your research work in this area.

Deep Learning

"Ultimately, major progress in artificial intelligence will come about through systems that combine representation learning with complex reasoning."

--Yann LeCun, Yoshua Bengio & Geoffrey Hinton--

"Being alchemy is certainly not a shame, not wanting to work on advancing to chemistry is a shame!"

--Eric Xing--

Graph Networks

"A graph neural network (GNN) is a class of neural network for processing data best represented by graph data structures."

--WIKIPEDIA--

"A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of convolutional neural networks which operate directly on graphs."

--Thomas N. Kipf and Max Welling--

Game Theory

Game theory is not only related to what we call "games (e.g., video games)" today. It is mainly concerned with the decision-making process in situations where outcomes are influenced by actions made by every rational/self-interested player. In addition, the players' choices determine the outcome of the game, but each player has only partial control of the outcome.