Alert button
Picture for Yaqi Duan

Yaqi Duan

Alert button

Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces

Jan 10, 2024
Yaqi Duan, Martin J. Wainwright

Viaarxiv icon

Policy evaluation from a single path: Multi-step methods, mixing and mis-specification

Nov 07, 2022
Yaqi Duan, Martin J. Wainwright

Figure 1 for Policy evaluation from a single path: Multi-step methods, mixing and mis-specification
Figure 2 for Policy evaluation from a single path: Multi-step methods, mixing and mis-specification
Figure 3 for Policy evaluation from a single path: Multi-step methods, mixing and mis-specification
Viaarxiv icon

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Mar 11, 2022
Ming Yin, Yaqi Duan, Mengdi Wang, Yu-Xiang Wang

Figure 1 for Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
Viaarxiv icon

Adaptive and Robust Multi-task Learning

Feb 10, 2022
Yaqi Duan, Kaizheng Wang

Figure 1 for Adaptive and Robust Multi-task Learning
Figure 2 for Adaptive and Robust Multi-task Learning
Figure 3 for Adaptive and Robust Multi-task Learning
Viaarxiv icon

Optimal policy evaluation using kernel-based temporal difference methods

Sep 24, 2021
Yaqi Duan, Mengdi Wang, Martin J. Wainwright

Figure 1 for Optimal policy evaluation using kernel-based temporal difference methods
Figure 2 for Optimal policy evaluation using kernel-based temporal difference methods
Figure 3 for Optimal policy evaluation using kernel-based temporal difference methods
Figure 4 for Optimal policy evaluation using kernel-based temporal difference methods
Viaarxiv icon

PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows

Jul 13, 2021
Aihua Mao, Zihui Du, Junhui Hou, Yaqi Duan, Yong-jin Liu, Ying He

Figure 1 for PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows
Figure 2 for PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows
Figure 3 for PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows
Figure 4 for PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows
Viaarxiv icon

Learning Good State and Action Representations via Tensor Decomposition

May 03, 2021
Chengzhuo Ni, Anru Zhang, Yaqi Duan, Mengdi Wang

Figure 1 for Learning Good State and Action Representations via Tensor Decomposition
Figure 2 for Learning Good State and Action Representations via Tensor Decomposition
Figure 3 for Learning Good State and Action Representations via Tensor Decomposition
Figure 4 for Learning Good State and Action Representations via Tensor Decomposition
Viaarxiv icon

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning

Mar 25, 2021
Yaqi Duan, Chi Jin, Zhiyuan Li

Figure 1 for Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Figure 2 for Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
Viaarxiv icon

Bootstrapping Statistical Inference for Off-Policy Evaluation

Feb 09, 2021
Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári, Mengdi Wang

Figure 1 for Bootstrapping Statistical Inference for Off-Policy Evaluation
Figure 2 for Bootstrapping Statistical Inference for Off-Policy Evaluation
Figure 3 for Bootstrapping Statistical Inference for Off-Policy Evaluation
Figure 4 for Bootstrapping Statistical Inference for Off-Policy Evaluation
Viaarxiv icon

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

Nov 08, 2020
Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvári, Mengdi Wang

Viaarxiv icon