etaoxing/multigame-dt
Implementation of Multi-Game Decision Transformers in PyTorch
This project helps AI researchers and reinforcement learning practitioners explore and understand how Decision Transformers perform across multiple different game environments. It takes pre-trained model weights for these 'multi-game' agents as input and allows you to run them to observe their performance in various tasks like 'Breakout', providing insights into their generalization capabilities. The primary users are machine learning researchers focused on AI agents and their application in diverse scenarios.
No commits in the last 6 months.
Use this if you are a researcher or AI developer who wants to run and evaluate existing Multi-Game Decision Transformer models on common reinforcement learning benchmarks.
Not ideal if you are looking for a tool to develop or train new AI agents from scratch, or if you are not familiar with reinforcement learning concepts and environments.
Stars
49
Forks
6
Language
Python
License
MIT
Category
Last pushed
Feb 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/etaoxing/multigame-dt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
transformerlab/transformerlab-app
The open source research environment for AI researchers to seamlessly train, evaluate, and scale...
naru-project/naru
Neural Relation Understanding: neural cardinality estimators for tabular data
neurocard/neurocard
State-of-the-art neural cardinality estimators for join queries
danielzuegner/code-transformer
Implementation of the paper "Language-agnostic representation learning of source code from...
salesforce/CodeTF
CodeTF: One-stop Transformer Library for State-of-the-art Code LLM