Why sparsify RL networks?
Static sparsity offers a surprisingly simple way to improve scaling in deep RL.
Greatness cannot
be planned.
So I play with joyful explorations.
I’m Guozheng, a PhD student at NTU, advised by Dacheng Tao. I study how reinforcement learning agents can scale, adapt, and keep learning.
Notes
All notesKeeping visual RL able to learn
Data, the critic and the timing of updates all shape an agent's learning capacity.
Learning from a different view
Useful visual diversity depends on both the transformation and the way it enters training.
Selected research
All publicationsBeyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors
Let deployment evidence guide how online learners use and adapt their offline priors.
What Makes Value Learning Efficient in Residual Reinforcement Learning?
Helping residual RL critics learn from a pretrained policy and recognize small action corrections.
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
Randomly pruning a network before training improves how deep RL scales.