jlin816 / dynalangLinks
Code for "Learning to Model the World with Language." ICML 2024 Oral.
☆413Updated 2 years ago
Alternatives and similar repositories for dynalang
Users that are interested in dynalang are comparing it to the libraries listed below
Sorting:
- STEVE-1: A Generative Model for Text-to-Behavior in Minecraft☆199Updated last year
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆94Updated 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. …☆144Updated last year
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆276Updated last month
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆268Updated last year
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆243Updated last month
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆290Updated 2 years ago
- [ICLR 2024] Source codes for the paper "Building Cooperative Embodied Agents Modularly with Large Language Models"☆286Updated 8 months ago
- Foundation Model for MineDojo☆286Updated 2 years ago
- ☆96Updated last year
- ☆439Updated 2 years ago
- Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"☆277Updated 3 years ago
- [ECCV2024] 🐙Octopus, an embodied vision-language model trained with RLEF, emerging superior in embodied visual planning and programming.☆293Updated last year
- [ICLR 2024 Spotlight] Text2Reward: Reward Shaping with Language Models for Reinforcement Learning☆191Updated 11 months ago
- ☆221Updated 2 years ago
- JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models☆385Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆133Updated 2 years ago
- General multi-task deep RL Agent☆185Updated last year
- Code for Contrastive Preference Learning (CPL)☆177Updated last year
- ☆144Updated last year
- ☆108Updated this week
- Implementation of "Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction"☆46Updated 2 years ago
- SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks☆320Updated last year
- An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic mult…☆72Updated 2 years ago
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos (ICLR'24, Spotlight)☆65Updated last year
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆312Updated this week
- CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.☆131Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆114Updated last year
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning☆596Updated 4 months ago
- The repository for the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).☆495Updated last year