近期论文5
- Provably Correct Optimization and Exploration with Non-linear Policies第 3 位,共 4 位作者ICML 2021 · 13 次引用
- FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs第 1 位,共 4 位作者NeurIPS 2020 · 271 次引用
- Safe Reinforcement Learning via Curriculum Induction第 5 位,共 5 位作者NeurIPS 2020 · 109 次引用
- Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration第 3 位,共 4 位作者NeurIPS 2020 · 97 次引用
- Policy Improvement via Imitation of Multiple Oracles第 3 位,共 3 位作者NeurIPS 2020 · 36 次引用
