Profiles2020-2022
Shangtong Zhang
University of Oxford
8Papers
0Last author
10Unique co-authors
6First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers8
- Learning Expected Emphatic Traces for Deep RLAuthor 2 of 4AAAI 2022 · 14 citations
- Breaking the Deadly Triad with a Target NetworkAuthor 1 of 3ICML 2021 · 61 citations
- Mean-Variance Policy Iteration for Risk-Averse Reinforcement LearningAuthor 1 of 3AAAI 2021 · 44 citations
- Average-Reward Off-Policy Policy Evaluation with Function ApproximationAuthor 1 of 4ICML 2021 · 39 citations
- GradientDICE: Rethinking Generalized Offline Estimation of Stationary ValuesAuthor 1 of 3ICML 2020 · 107 citations
- Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function ApproximationAuthor 1 of 4ICML 2020 · 58 citations
- Mega-Reward: Achieving Human-Level Play without Extrinsic RewardsAuthor 5 of 7AAAI 2020 · 18 citations
- Learning Retrospective Knowledge with Reverse Reinforcement LearningAuthor 1 of 3NeurIPS 2020 · 13 citations
