Shalev-Lifshitz / STEVE-1Links
STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
☆194Updated last year
Alternatives and similar repositories for STEVE-1
Users that are interested in STEVE-1 are comparing it to the libraries listed below
Sorting:
- Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"☆94Updated 2 years ago
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆392Updated 2 years ago
- Foundation Model for MineDojo☆277Updated 2 years ago
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos (ICLR 2024 Spotlight)☆65Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆108Updated last year
- Implementation of "Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction"☆46Updated 2 years ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models☆378Updated 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
- [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking☆270Updated last year
- ☆94Updated last year
- Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agen…☆285Updated 2 years ago
- Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).☆239Updated last week
- ☆44Updated last year
- General multi-task deep RL Agent☆184Updated last year
- OMNI: Open-endedness via Models of human Notions of Interestingness☆57Updated 7 months ago
- ☆108Updated 3 months ago
- We perform functional grounding of LLMs' knowledge in BabyAI-Text☆273Updated last year
- BASALT Benchmark datasets, evaluation code and agent training example.☆21Updated last year
- Benchmarking Agentic LLM and VLM Reasoning On Games☆193Updated last month
- CivRealm is an interactive environment for the open-source strategy game Freeciv-web based on Freeciv, a Civilization-inspired game.☆126Updated last year
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆136Updated last year
- ☆219Updated 2 years ago
- ☆144Updated last year
- ☆101Updated last year
- This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."☆33Updated 2 months ago
- ☆112Updated 5 months ago
- [ICLR 2024 Spotlight] Code for the paper "Text2Reward: Reward Shaping with Language Models for Reinforcement Learning"☆177Updated 9 months ago
- ☆36Updated 3 years ago
- Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs☆96Updated 6 months ago