Alert button
Picture for Yu Bai

Yu Bai

Alert button

The Role of Coverage in Online Reinforcement Learning

Oct 09, 2022
Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade

Figure 1 for The Role of Coverage in Online Reinforcement Learning
Viaarxiv icon

Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms

Sep 29, 2022
Fan Chen, Yu Bai, Song Mei

Figure 1 for Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
Viaarxiv icon

Unified Algorithms for RL with Decision-Estimation Coefficients: No-Regret, PAC, and Reward-Free Learning

Sep 23, 2022
Fan Chen, Song Mei, Yu Bai

Viaarxiv icon

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

Jun 08, 2022
Eshaan Nichani, Yu Bai, Jason D. Lee

Figure 1 for Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
Figure 2 for Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
Viaarxiv icon

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

Jun 06, 2022
Runyu Zhang, Qinghua Liu, Huan Wang, Caiming Xiong, Na Li, Yu Bai

Figure 1 for Policy Optimization for Markov Games: Unified Framework and Faster Convergence
Figure 2 for Policy Optimization for Markov Games: Unified Framework and Faster Convergence
Viaarxiv icon

Efficient $Φ$-Regret Minimization in Extensive-Form Games via Online Mirror Descent

Jun 02, 2022
Yu Bai, Chi Jin, Song Mei, Ziang Song, Tiancheng Yu

Viaarxiv icon

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games

May 15, 2022
Ziang Song, Song Mei, Yu Bai

Viaarxiv icon

PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization

Apr 09, 2022
Xiaochen Liu, Yu Bai, Jiawei Li, Yinan Hu, Yang Gao

Figure 1 for PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Figure 2 for PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Figure 3 for PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Figure 4 for PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Viaarxiv icon

Non-autoregressive Translation with Dependency-Aware Decoder

Mar 30, 2022
Jiaao Zhan, Qian Chen, Boxing Chen, Wen Wang, Yu Bai, Yang Gao

Figure 1 for Non-autoregressive Translation with Dependency-Aware Decoder
Figure 2 for Non-autoregressive Translation with Dependency-Aware Decoder
Figure 3 for Non-autoregressive Translation with Dependency-Aware Decoder
Figure 4 for Non-autoregressive Translation with Dependency-Aware Decoder
Viaarxiv icon