Name: Mengdi Li
Type: User
Company: University of Hamburg
Bio: PhD student at the University of Hamburg. Interested in RL, Robotics, and LLMs.
Twitter: limengdi2
Location: Hamburg, Germany
Blog: https://mengdi-li.github.io/
Mengdi Li's Projects
An open source framework for research in Embodied-AI from AI2.
A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)
A set of configuration files
[ICML 2023] Code for paper "Internally Rewarded Reinforcement Learning"
Pytorch implementation of the MAC-Network
A TensorFlow implementation for "Recurrent Attention Network on Memory for Aspect Sentiment Analysis"
PyTorch implementation of "Robotic Occlusion Reasoning for Efficient Object Existence Prediction" (IROS 2021)
Code for "Systematic Generalization: What Is Required and Can It Be Learned"
Train transformer language models with reinforcement learning.
记录UNO自定义版本规则。