Profiles2020-2021
Ruosong Wang
Carnegie Mellon University
17Papers
2Last author
18Unique co-authors
6First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers17
- Bilinear Classes: A Structural Framework for Provable Generalization in RLAuthor 7 of 7ICML 2021 · 207 citations
- What are the Statistical Limits of Offline RL with Linear Function Approximation?Author 1 of 3ICLR 2021 · 172 citations
- Optimism in Reinforcement Learning with Generalized Linear Function ApproximationAuthor 2 of 4ICLR 2021 · 54 citations
- An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality GapAuthor 2 of 3NeurIPS 2021 · 48 citations
- Instabilities of Offline RL with Pre-Trained Neural RepresentationAuthor 1 of 4ICML 2021 · 46 citations
- Settling the Horizon-Dependence of Sample Complexity in Reinforcement LearningAuthor 2 of 3FOCS 2021 · 3 citations
- Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?Author 3 of 4ICLR 2020 · 213 citations
- Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder DimensionAuthor 1 of 3NeurIPS 2020 · 168 citations
- Harnessing the Power of Infinitely Wide Deep Nets on Small-data TasksAuthor 5 of 6ICLR 2020 · 167 citations
- On Reward-Free Reinforcement Learning with Linear Function ApproximationAuthor 1 of 4NeurIPS 2020 · 121 citations
- Is Long Horizon RL More Difficult Than Short Horizon RL?Author 1 of 4NeurIPS 2020 · 28 citations
- Planning with General Objective Functions: Going Beyond Total RewardsAuthor 1 of 5NeurIPS 2020 · 23 citations
- Agnostic -learning with Function Approximation in Deterministic Systems: Near-Optimal Bounds on Approximation Error and Sample ComplexityAuthor 4 of 4NeurIPS 2020 · 19 citations
- The Communication Complexity of OptimizationAuthor 3 of 4SODA 2020 · 16 citations
- Provably Efficient Exploration for Reinforcement Learning Using Unsupervised LearningAuthor 2 of 5NeurIPS 2020 · 13 citations
- Nearly Linear Row Sampling Algorithm for Quantile RegressionAuthor 2 of 4ICML 2020 · 7 citations
- Tight Bounds for the Subspace Sketch Problem with ApplicationsAuthor 2 of 3SODA 2020 · 5 citations
