flowersteam / Grounding_LLMs_with_online_RL
We perform functional grounding of LLMs' knowledge in BabyAI-Text
☆250Updated 7 months ago
Alternatives and similar repositories for Grounding_LLMs_with_online_RL:
Users that are interested in Grounding_LLMs_with_online_RL are comparing it to the libraries listed below
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆222Updated 4 months ago
- Implementation of TWOSOME☆67Updated 2 months ago
- Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)☆160Updated last year
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆135Updated 11 months ago
- ☆216Updated last year
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆247Updated 5 months ago
- Official code repository for Prompt-DT.☆107Updated 2 years ago
- [ICLR 2024 Spotlight] Code for the paper "Text2Reward: Reward Shaping with Language Models for Reinforcement Learning"☆154Updated 3 months ago
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆379Updated last year
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆91Updated last year
- Code for Contrastive Preference Learning (CPL)☆162Updated 4 months ago
- a simple and scalable agent for training adaptive policies with sequence-based RL☆115Updated last month
- ☆74Updated last year
- A RL approach to enable cost-effective, intelligent interactions between a local agent and a remote LLM☆70Updated 7 months ago
- A collection of LLM with RL papers☆265Updated 11 months ago
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆205Updated last year
- ☆84Updated 8 months ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆270Updated last year
- CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.☆108Updated 6 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆153Updated 11 months ago
- A large-scale multi-modal pre-trained model☆131Updated 2 years ago
- A comprehensive list of PAPERS, CODEBASES, and, DATASETS on Decision Making using Foundation Models including LLMs and VLMs.☆362Updated 11 months ago
- Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]☆122Updated 2 years ago
- Reinforcement learning and planning for Minecraft.☆173Updated last year
- Overcooked human-AI experiment platform☆37Updated last year
- ☆27Updated last year
- PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tu…☆144Updated last year
- [ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"☆248Updated 2 weeks ago
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆66Updated last year
- ☆218Updated 4 months ago