abenechehab/dicl
[ICLR 2025] Official implementation of DICL (Disentangled In-Context Learning), featured in the paper "Zero-shot Model-based Reinforcement Learning using Large Language Models".
This project helps operations engineers, automation specialists, and control system designers predict how complex, interacting systems will behave. You provide historical data about system states and actions taken, and it outputs predictions for future system dynamics. This is especially useful for those working with robotics, autonomous vehicles, or industrial control where understanding future behavior is crucial for decision-making.
No commits in the last 6 months.
Use this if you need to forecast the dynamics of multivariate time series in continuous control systems or want to evaluate policies in complex environments without extensive new data.
Not ideal if your primary goal is text-based reinforcement learning or if you are working with discrete state spaces, as it's optimized for continuous, multivariate data.
Stars
25
Forks
4
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/abenechehab/dicl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.