Shalev-Lifshitz / STEVE-1
STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
☆172Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for STEVE-1
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆86Updated last year
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆365Updated last year
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos☆56Updated 11 months ago
- Implementation of "Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction"☆42Updated last year
- Foundation Model for MineDojo☆242Updated last year
- Intrinsic Motivation from Artificial Intelligence Feedback☆120Updated last year
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆121Updated 7 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆84Updated 2 months ago
- JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models☆339Updated 7 months ago
- ☆74Updated 4 months ago
- ☆76Updated 5 months ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆72Updated 3 months ago
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆252Updated 4 months ago
- General multi-task deep RL Agent☆165Updated 5 months ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆196Updated 2 weeks ago
- ☆40Updated 11 months ago
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆255Updated last year
- a simple and scalable agent for training adaptive policies with sequence-based RL☆93Updated this week
- ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.☆222Updated last month
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆114Updated 9 months 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…☆62Updated last year
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆85Updated last year
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆221Updated 3 months ago
- MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft☆16Updated last year
- [ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"☆129Updated last month
- ☆137Updated 6 months ago
- Official Repo of LangSuitE☆78Updated 3 months ago
- Code for Contrastive Preference Learning (CPL)☆154Updated this week
- Bootstrapping ARC☆65Updated this week
- OMNI: Open-endedness via Models of human Notions of Interestingness☆39Updated 11 months ago