Pinned Loading

1. fewshot-preference-optimization fewshot-preference-optimization Public

   Few-Shot Preference Optimization (FSPO) personalizes LLMs by reframing reward modeling as a meta-learning problem, enabling rapid adaptation to user preferences with minimal labeled data, leveragin…

   Python 11 4

2. understanding-rlhf understanding-rlhf Public

   Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Our new work finds that approaches employing on-policy samplin…

   Python 30 4

3. PTR PTR Public

   This repository contains the implementation of the PTR algorithm described in the paper: Pre-Training for Robots: Leveraging Diverse Multitask Data via Offline Reinforcement Learning.

   Python 28 3

4. OfflineRlWorkflow OfflineRlWorkflow Public

   This repository accompanies the following paper: A Workflow for Offline Model-Free Robotic RL

   Python 11 2

5. Cal-QL Cal-QL Public

   A method that learns a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q…

   Python

6. Personalized-Text-To-Image-Diffusion Personalized-Text-To-Image-Diffusion Public

   Public Implementation of PPD

   Python 8