Cornell-RL / drpoLinks
Dateset Reset Policy Optimization
☆30Updated last year
Alternatives and similar repositories for drpo
Users that are interested in drpo are comparing it to the libraries listed below
Sorting:
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆29Updated last year
- Natural Language Reinforcement Learning☆92Updated 6 months ago
- ☆144Updated 7 months ago
- Directional Preference Alignment☆58Updated 9 months ago
- Advantage Leftover Lunch Reinforcement Learning (A-LoL RL): Improving Language Models with Advantage-based Offline Policy Gradients☆26Updated 10 months ago
- ☆87Updated last year
- Implementation of ICLR 2025 paper "Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation"☆17Updated 9 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆58Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆44Updated last year
- SCoRe: Training Language Models to Self-Correct via Reinforcement Learning☆10Updated 5 months ago
- Self-Supervised Alignment with Mutual Information☆20Updated last year
- Bayes-Adaptive RL for LLM Reasoning☆37Updated last month
- NeurIPS 2024 tutorial on LLM Inference☆45Updated 7 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆25Updated last year
- ☆19Updated 4 months ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated last year
- ☆26Updated last year
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆30Updated last year
- ☆61Updated 4 months ago
- ☆33Updated 10 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆44Updated 3 months ago
- Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (ACL 2024)☆69Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- ☆20Updated last year
- RL algorithm: Advantage induced policy alignment☆65Updated last year
- ☆114Updated 5 months ago
- ☆47Updated last month
- Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF☆20Updated 9 months ago
- ☆52Updated 5 months ago
- Repository for Skill Set Optimization☆14Updated 11 months ago