Zhao Yang

I am a PhD student at Leiden University, supervised by Thomas Moerland, Mike Preuss, and Aske Plaat. I got my master degree at Leiden University, then joined Reinforcement Learning Group as a PhD student in 2020.

I'm interested in reinforcement learning and try to automate RL agents using [intrinsic motivation, world model ...]

Contact: z.yang(at)liacs.leidenuniv.nl
Google Scholar | LinkedIn | Twitter | Github | CV

Research

	Two-Memory Reinforcement Learning Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat COG, 2023 Arxiv \| Code Combine episodic control and DRL together to benefit from both sides.
	Continuous Episodic Control Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat COG, 2023 Arxiv \| Code Use episodic memory directly for continuous action selection.
	First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat ICAART, 2023; ALOE workshop @ICLR, 2022 Arxiv Systematically illustrate that why and how Go-Explore works in tabular and deep RL settings.
	Transfer Learning and Curriculum Learning in Sokoban Zhao Yang, Mike Preuss, Aske Plaat BNAIC, 2021 Arxiv Pre-train and fine-tune neural networks on Sokoban tasks.

Latest update: 09/2023