tedmoskovitz / ConstrainedRL4LMsLinks
A library for constrained RLHF.
☆13Updated last year
Alternatives and similar repositories for ConstrainedRL4LMs
Users that are interested in ConstrainedRL4LMs are comparing it to the libraries listed below
Sorting:
- ☆110Updated last year
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆185Updated 8 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆202Updated 9 months ago
- A repo for RLHF training and BoN over LLMs, with support for reward model ensembles.☆46Updated last year
- Rewarded soups official implementation☆62Updated 2 years ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆244Updated last month
- Direct preference optimization with f-divergences.☆16Updated last year
- (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training☆285Updated last year
- Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)☆199Updated 2 years ago
- ☆14Updated last year
- Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —☆281Updated 5 months ago
- Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)☆42Updated last year
- A collection of LLM with RL papers☆278Updated last year
- [NeurIPS 2023] Large Language Models Are Semi-Parametric Reinforcement Learning Agents☆39Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆124Updated last year
- RLHF implementation details of OAI's 2019 codebase☆197Updated 2 years ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆47Updated 2 years ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆275Updated 3 months ago
- Reasoning with Language Model is Planning with World Model☆185Updated 2 years ago
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆145Updated last year
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆79Updated 7 months ago
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆336Updated 2 months ago
- Benchmarking Agentic LLM and VLM Reasoning On Games☆228Updated 2 months ago
- ☆185Updated 2 years ago
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆56Updated last year
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆211Updated 2 years ago
- Code release for "Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search" published at NeurIPS '24.☆17Updated 11 months ago
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆32Updated last year
- Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"☆46Updated 11 months ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆28Updated 2 years ago