On the Estimation Bias in Double Q-Learning

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 13 of 36
1. Verfasser: Ren, Zhizhou (VerfasserIn)
Weitere Verfasser: Zhu, Guangxiang (VerfasserIn), Hu, Hao (VerfasserIn), Han, Beining (VerfasserIn), Chen, Jianglun (VerfasserIn), Zhang, Chongjie (VerfasserIn)
Pages:35
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2022
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives 2022 Qi, Qi
Contrastively Disentangled Sequential Variational Autoencoder 2022 Bai, Junwen
Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions 2022 Loureiro, Bruno
List-Decodable Mean Estimation in Nearly-PCA Time 2022 Diakonikolas, Ilias
Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space 2022 Ghimire, Sandesh
Escaping Saddle Points with Compressed SGD 2022 Avdiukhin, Dmitrii
Mitigating Forgetting in Online Continual Learning with Neuron Calibration 2022 Yin, Haiyan
K-Net: Towards Unified Image Segmentation 2022 Zhang, Wenwei
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning 2022 Yang, Yiqin
Faster Matchings via Learned Duals 2022 Dinitz, Michael
Modality-Agnostic Topology Aware Localization 2022 Ghazvinian Zanjani, Farhad
Curriculum Design for Teaching via Demonstrations: Theory and Applications 2022 Yengera, Gaurav
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity 2022 Liu, Ran
Local Differential Privacy for Regret Minimization in Reinforcement Learning 2022 Garcelon, Evrard
Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation 2022 Zhao, Jingyu
Universal Graph Convolutional Networks 2022 Jin, Di
Independent Prototype Propagation for Zero-Shot Compositionality 2022 Ruis, Frank
Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition 2022 Boss, Mark
Information is Power: Intrinsic Control via Information Capture 2022 Rhinehart, Nicholas
Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization 2022 Peng, Zhenghao
Alle Artikel auflisten