How Over-Parameterization Slows Down Gradient Descent
Offline Multi-agent Reinforcement Learning
Passive and Active Multi-Task Representation Learning
Is Reinforcement Learning More Difficult Than Bandits? Horizon-Free Regret Bounds of Reinforcement Learning
On Reinforcement Learning with Large State Space and Long Horizon
Nearly Minimax Optimal Reward-free Reinforcement Learning
Provable Representation Learning
Ultra-wide Neural Networks and Neural Tangent Kernel