Pinned Loading

1. RewardModelingBeyondBradleyTerry RewardModelingBeyondBradleyTerry Public

   official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives

   Python 55 3

2. RewardShifting RewardShifting Public

   Code for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL

   Python 29 3

3. Prompt-OIRL Prompt-OIRL Public

   code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning

   Python 40 6

4. embedding-based-llm-alignment embedding-based-llm-alignment Public

   Codebase for Paper Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs

   Python 12 1

5. Inverse-RLignment Inverse-RLignment Public

   inverse reinforcement learning for LLM alignment