liziniu / policy_optimization
Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)
☆28Updated last year
Alternatives and similar repositories for policy_optimization:
Users that are interested in policy_optimization are comparing it to the libraries listed below
- Rewarded soups official implementation☆58Updated last year
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆25Updated last year
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆54Updated 3 weeks ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 3 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆43Updated last year
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆53Updated 10 months ago
- A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.☆43Updated 3 months ago
- ☆40Updated last year
- Directional Preference Alignment☆57Updated 7 months ago
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆75Updated 8 months ago
- ☆15Updated 5 months ago
- Code for the paper: Dense Reward for Free in Reinforcement Learning from Human Feedback (ICML 2024) by Alex J. Chan, Hao Sun, Samuel Holt…☆28Updated 8 months ago
- Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"☆32Updated 2 months ago
- Dateset Reset Policy Optimization☆30Updated last year
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆43Updated last week
- ☆30Updated 5 months ago
- ☆30Updated last year
- Self-Supervised Alignment with Mutual Information☆17Updated 11 months ago
- An index of algorithms for reinforcement learning from human feedback (rlhf))☆93Updated last year
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆28Updated last year
- ☆33Updated last month
- Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients☆26Updated 7 months ago
- What Makes a Reward Model a Good Teacher? An Optimization Perspective☆23Updated 2 weeks ago
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆24Updated 3 months ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆16Updated 5 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆64Updated 4 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 7 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆29Updated 7 months ago
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆136Updated 2 months ago
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆25Updated 4 months ago