Sea-Snell / Implicit-Language-Q-LearningLinks
Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"
☆209Updated 2 years ago
Alternatives and similar repositories for Implicit-Language-Q-Learning
Users that are interested in Implicit-Language-Q-Learning are comparing it to the libraries listed below
Sorting:
- Code accompanying the paper Pretraining Language Models with Human Preferences☆180Updated last year
- ☆99Updated last year
- ☆159Updated 2 years ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆167Updated 3 months ago
- RL algorithm: Advantage induced policy alignment☆65Updated 2 years ago
- Simple next-token-prediction for RLHF☆227Updated last year
- ☆127Updated last year
- ☆210Updated 2 years ago
- Code for Contrastive Preference Learning (CPL)☆175Updated 9 months ago
- A (somewhat) minimal library for finetuning language models with PPO on human feedback.☆86Updated 2 years ago
- [NeurIPS 2023] Learning Transformer Programs☆163Updated last year
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆66Updated 2 years ago
- A repository for transformer critique learning and generation☆90Updated last year
- ☆84Updated last year
- RLHF implementation details of OAI's 2019 codebase☆190Updated last year
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆140Updated last year
- ☆83Updated last year
- ☆219Updated 2 years ago
- ☆185Updated last year
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆45Updated last year
- Reinforcement Learning via Regressing Relative Rewards☆35Updated 8 months ago
- ☆119Updated last year
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆271Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- ☆150Updated 9 months ago
- Reasoning with Language Model is Planning with World Model☆169Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆188Updated 2 years ago
- Train very large language models in Jax.☆206Updated last year
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆237Updated last week
- Self-Alignment with Principle-Following Reward Models☆165Updated 3 months ago