pranavAL/DART
Official Code Repo for the paper "Learning to Play Atari in a World of Tokens" accepted at ICML, 2024
This project provides an advanced method for training AI to play complex video games, particularly older arcade-style games, with high efficiency. It takes raw game screen inputs and learns to make optimal decisions, resulting in an AI that can play and often outperform humans in various game scenarios. The primary users are AI researchers and developers focused on reinforcement learning and game AI.
No commits in the last 6 months.
Use this if you are an AI researcher developing sample-efficient agents for complex sequential decision-making tasks, especially in environments like video games.
Not ideal if you are looking for a plug-and-play solution for a business application or a tool for general machine learning tasks outside of reinforcement learning research.
Stars
11
Forks
—
Language
—
License
—
Category
Last pushed
Jun 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pranavAL/DART"
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.