Alert button
Picture for Jinyi Liu

Jinyi Liu

Alert button

vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement

Add code
Bookmark button
Alert button
May 14, 2024
Yiwen Zhu, Jinyi Liu, Wenya Wei, Qianyi Fu, Yujing Hu, Zhou Fang, Bo An, Jianye Hao, Tangjie Lv, Changjie Fan

Viaarxiv icon

SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models

Add code
Bookmark button
Alert button
Mar 06, 2024
Yibin Chen, Yifu Yuan, Zeyu Zhang, Yan Zheng, Jinyi Liu, Fei Ni, Jianye Hao

Figure 1 for SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models
Figure 2 for SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models
Figure 3 for SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models
Figure 4 for SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models
Viaarxiv icon

Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models

Add code
Bookmark button
Alert button
Feb 22, 2024
Jinyi Liu, Yifu Yuan, Jianye Hao, Fei Ni, Lingzhi Fu, Yibin Chen, Yan Zheng

Viaarxiv icon

Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback

Add code
Bookmark button
Alert button
Feb 04, 2024
Yifu Yuan, Jianye Hao, Yi Ma, Zibin Dong, Hebin Liang, Jinyi Liu, Zhixin Feng, Kai Zhao, Yan Zheng

Viaarxiv icon

A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure

Add code
Bookmark button
Alert button
Jan 03, 2024
Yanjie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao

Viaarxiv icon

OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments

Add code
Bookmark button
Alert button
Dec 20, 2023
Jinyi Liu, Zhi Wang, Yan Zheng, Jianye Hao, Chenjia Bai, Junjie Ye, Zhen Wang, Haiyin Piao, Yang Sun

Viaarxiv icon

MetaSymNet: A Dynamic Symbolic Regression Network Capable of Evolving into Arbitrary Formulations

Add code
Bookmark button
Alert button
Nov 13, 2023
Yanjie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng

Viaarxiv icon

Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning

Add code
Bookmark button
Alert button
Jun 27, 2023
Jinyi Liu, Yi Ma, Jianye Hao, Yujing Hu, Yan Zheng, Tangjie Lv, Changjie Fan

Figure 1 for Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
Figure 2 for Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
Figure 3 for Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
Figure 4 for Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
Viaarxiv icon

Ensemble-based Offline-to-Online Reinforcement Learning: From Pessimistic Learning to Optimistic Exploration

Add code
Bookmark button
Alert button
Jun 12, 2023
Kai Zhao, Yi Ma, Jinyi Liu, Yan Zheng, Zhaopeng Meng

Figure 1 for Ensemble-based Offline-to-Online Reinforcement Learning: From Pessimistic Learning to Optimistic Exploration
Figure 2 for Ensemble-based Offline-to-Online Reinforcement Learning: From Pessimistic Learning to Optimistic Exploration
Figure 3 for Ensemble-based Offline-to-Online Reinforcement Learning: From Pessimistic Learning to Optimistic Exploration
Figure 4 for Ensemble-based Offline-to-Online Reinforcement Learning: From Pessimistic Learning to Optimistic Exploration
Viaarxiv icon

HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach

Add code
Bookmark button
Alert button
Jun 10, 2023
Shixi Lian, Yi Ma, Jinyi Liu, Yan Zheng, Zhaopeng Meng

Figure 1 for HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach
Figure 2 for HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach
Figure 3 for HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach
Figure 4 for HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach
Viaarxiv icon