jlin816/dynalang
Code for "Learning to Model the World with Language." ICML 2024 Oral.
This project helps researchers in artificial intelligence develop agents that can understand and interact with simulated environments using language. It takes various forms of language data, such as task descriptions or instructions, and environmental observations (like images or sensor data) as input. The output is an agent capable of predicting future outcomes and performing tasks more effectively within these simulated worlds. It's intended for AI researchers and practitioners working on embodied AI, reinforcement learning, and natural language understanding.
414 stars.
Use this if you are an AI researcher developing agents that need to interpret and utilize language to model their environment and solve tasks within simulated settings.
Not ideal if you are looking for a plug-and-play solution for real-world robotics or a general-purpose natural language processing library.
Stars
414
Forks
31
Language
Python
License
—
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jlin816/dynalang"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Goekdeniz-Guelmez/mlx-lm-lora
Train Large Language Models on MLX.
uber-research/PPLM
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
VHellendoorn/Code-LMs
Guide to using pre-trained large language models of source code
ssbuild/chatglm_finetuning
chatglm 6b finetuning and alpaca finetuning
jarobyte91/pytorch_beam_search
A lightweight implementation of Beam Search for sequence models in PyTorch.