eloialonso/iris
Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
This project helps researchers and AI practitioners develop and train agents that can learn effectively from limited experience in virtual environments, like classic arcade games. You input raw visual observations from an environment, and it outputs an intelligent agent capable of understanding and interacting with that environment, learning how to achieve goals with significantly less data than traditional methods. This is ideal for those building or studying advanced AI agents.
870 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer focused on creating AI agents that can learn quickly and efficiently in complex simulated environments.
Not ideal if you are looking for a pre-trained, ready-to-deploy agent for a specific real-world task or a simple reinforcement learning library for beginner-level projects.
Stars
870
Forks
92
Language
Python
License
GPL-3.0
Category
Last pushed
Oct 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/eloialonso/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.