Mengdi Wang
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 3 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Policy Gradient: Optimal Estimation, Convergence, and Generalization beyond Cumulative Rewards | Adversarial Approaches in Machine Learning 2022 | 2022-02-17 |
Shows that policy gradients obey a policy-gradient Bellman equation and uses a practical double fitted iteration (regression over Q and its gradient) to get a… | ||
| Model-Based Reinforcement Learning with Value-Targeted Regression | Mathematics of Online Decision Making 2020 | 2020-10-23 |
Proposes using value-targeted regression: fit transition models only to predict next-step value estimates, then build confidence sets over models and do… | ||
| Reinforcement Learning in Feature Space: Complexity and Regret | Emerging Challenges in Deep Learning (Simons Institute workshop, 2019) | 2019-08-05 |
Shows that tabular sample complexity reaches the known S A / (1−γ)^3 type limits, then moves to low‑rank transition kernel: P(s'|s,a)=φ(s,a)^T M ψ(s') and… | ||
| nothing matches | ||