Picture for Liangpeng Zhang

Liangpeng Zhang

A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning

Add code
Oct 18, 2024
Viaarxiv icon

Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection

Add code
Apr 26, 2017
Figure 1 for Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection
Figure 2 for Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection
Figure 3 for Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection
Viaarxiv icon

Success Probability of Exploration: a Concrete Analysis of Learning Efficiency

Add code
Dec 02, 2016
Figure 1 for Success Probability of Exploration: a Concrete Analysis of Learning Efficiency
Figure 2 for Success Probability of Exploration: a Concrete Analysis of Learning Efficiency
Figure 3 for Success Probability of Exploration: a Concrete Analysis of Learning Efficiency
Figure 4 for Success Probability of Exploration: a Concrete Analysis of Learning Efficiency
Viaarxiv icon