vmicheli/delta-iris
Efficient World Models with Context-Aware Tokenization. ICML 2024
This project helps researchers and engineers develop and evaluate reinforcement learning agents more efficiently. It takes environmental data, such as game frames, and uses it to train an agent within a simulated 'imagination' of the environment. The output is a trained agent capable of performing tasks in virtual environments, providing a powerful tool for AI development.
119 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer focused on developing and testing reinforcement learning algorithms and world models.
Not ideal if you are looking for a plug-and-play solution for real-world robotics or autonomous systems without deep understanding of reinforcement learning.
Stars
119
Forks
15
Language
Python
License
GPL-3.0
Category
Last pushed
Sep 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/vmicheli/delta-iris"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.