Portrait of Elaine Lau

Elaine Lau

Master's Research - McGill University
Supervisor
Research Topics
Reinforcement Learning

Publications

QGFN: Controllable Greediness with Action Values
Stephen Zhewen Lu
Ling Pan
Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating … (see more)diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate,
QGFN: Controllable Greediness with Action Values
Stephen Zhewen Lu
Ling Pan
Generative Flow Networks (GFlowNets; GFNs) are a family of reward/energy-based generative methods for combinatorial objects, capable of gene… (see more)rating diverse and high-utility samples. However, biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate,
DGFN: Double Generative Flow Networks
Nikhil Murali Vemgal
An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets
Nikhil Murali Vemgal
Reinforcement Learning (RL) algorithms aim to learn an optimal policy by iteratively sampling actions to learn how to maximize the total exp… (see more)ected return,
Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning
Nathan de Lara
Jacob A. Shkrob
My Duc Tran