STATISTICAL-COMPUTATIONAL TRADEOFF IN SINGLE INDEX MODELS

von Wang, Lingxiao
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 14 of 20 (2020)

COMPUTATIONAL-STATISTICAL TRADEOFFS IN INFERRING COMBINATORIAL STRUCTURES OF ISING MODEL

von Jin, Ying
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 7 of 15 (2021)

Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency

von Cai, Qi
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 4 of 33 (2023)

RISK-SENSITIVE REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION: A DEBIASING APPROACH

von FEI, YINGJIE
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 5 of 16 (2022)

IS PESSIMISM PROVABLY EFFICIENT FOR OFFLINE RL?

von JIN, YING
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 7 of 16 (2022)

Provably Efficient Causal Reinforcement Learning with Confounded Observational Data

von Wang, Lingxiao
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 25 of 36 (2022)

PROVABLY GLOBAL CONVERGENCE OF ACTOR-CRITIC: A CASE FOR LINEAR QUADRATIC REGULATOR WITH ERGODIC COST

von Yang, Zhuoran
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 11 of 20 (2020)

Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning

von Fei, Yingjie
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 25 of 36 (2022)

NEURAL TRUST REGION/PROXIMAL POLICY OPTIMIZATION ATTAINS GLOBALLY OPTIMAL POLICY

von Liu, Boyi
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 14 of 20 (2020)

END-TO-END LEARNING AND INTERVENTION IN GAMES

von Li, Jiayang
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 20 of 27 (2021)

Dynamic Regret of Policy Optimization in Non-Stationary Environments

von Fei, Yingjie
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 9 of 27 (2021)

Pessimism Meets VCG: Learning Dynamic Mechanism Design Via Offline Reinforcement Learning

von Lyu, Boxiang
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 18 of 33 (2023)

BooVI: Provably Efficient Bootstrapped Value Iteration

von Liu, Boyi
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 9 of 36 (2022)

DECENTRALIZED SINGLE-TIMESCALE ACTOR-CRITIC ON ZERO-SUM TWO-PLAYER STOCHASTIC GAMES

von GUO, HONGYI
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 5 of 16 (2022)

ON REWARD-FREE RL WITH KERNEL AND NEURAL FUNCTION APPROXIMATIONS: SINGLE-AGENT MDP AND MARKOV GAME

von QIU, SHUANG
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 11 of 16 (2022)

GLOBAL CONVERGENCE OF POLICY GRADIENT FOR LINEAR-QUADRATIC MEAN-FIELD CONTROL/GAME IN CONTINUOUS TIME

von WANG, WEICHEN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 14 of 16 (2022)

LEARNING WHILE PLAYING IN MEAN-FIELD GAMES: CONVERGENCE AND OPTIMALITY

von XIE, QIAOMIN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 15 of 16 (2022)

Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration

von Wu, Runzhe
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 30 of 36 (2022)

A Unifying Framework of Off-Policy General Value Function Evaluation

von Xu, Tengyu
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 18 of 50 (2023)

CONVERGENT POLICY OPTIMIZATION FOR SAFE REINFORCEMENT LEARNING

von Yu, Ming
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 4 of 20 (2020)