REGRET MINIMIZATION FOR REINFORCEMENT LEARNING BY EVALUATING THE OPTIMAL BIAS FUNCTION

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

MODEL-FREE REINFORCEMENT LEARNING: FROM CLIPPED PSEUDO-REGRET TO SAMPLE COMPLEXITY

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

ALMOST OPTIMAL MODEL-FREE REINFORCEMENT LEARNINGVIA REFERENCE- ADVANTAGE DECOMPOSITION

von Zhang, Zihan
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 19 of 27 (2021)

NEARLY OPTIMAL REWARD-FREE REINFORCEMENT LEARNING

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

CATRE: Iterative Point Clouds Alignment for Category-Level Object Pose Refinement

von Liu, Xingyu
Veröffentlicht in ECCV (17. : 2022 : Tel Aviv; Online) Computer vision – ECCV 2022 ; Part 2 (2022)

Weakly Supervised Learning of Instance Segmentation with Confidence Feedback

von Yang, Yu
Veröffentlicht in CICAI (2. : 2022 : Peking) Artificial intelligence ; Part 1 (2022)

Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning

von Zhang, Zihan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 32 of 50 (2023)

Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP

von Zhang, Zihan
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 6 of 36 (2022)

Distilling Representations from GAN Generator via Squeeze and Span

von Yang, Yu
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 44 of 50 (2023)

SPD: Synergy Pattern Diversifying Oriented Unsupervised Multi-agent Reinforcement Learning

von Jiang, Yuhang
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 27 of 50 (2023)

ASYMMETRIC LOSS FUNCTIONS FOR LEARNING WITH NOISY LABELS

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

RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation

von Zhang, Ruida
Veröffentlicht in ECCV (17. : 2022 : Tel Aviv; Online) Computer vision – ECCV 2022 ; Part 1 (2022)

Prototype-Anchored Learning for Learning with Imperfect Annotations

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

Self-Organized Group for Cooperative Multi-agent Reinforcement Learning

von Shao, Jianzhun
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 8 of 50 (2023)

Self6D: Self-supervised Monocular 6D Object Pose Estimation

von Wang, Gu
Veröffentlicht in ECCV (16. : 2020 : Online) Computer vision - ECCV 2020 ; Part 1 (2020)

Confidence Map Based 3D Cost Aggregation with Multiple Minimum Spanning Trees for Stereo Matching

von Xiao, Yuhao
Veröffentlicht in ACPR (5. : 2019 : Auckland) Pattern recognition ; Part 1 (2020)

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

von Shao, Zhuchen
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 3 of 36 (2022)

Improved Fine-Tuning by Better Leveraging Pre-Training Data

von Liu, Ziquan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 42 of 50 (2023)