ml-jku/RA-DT

Retrieval-Augmented Decision Transformer: External Memory for In-context RL

26
/ 100
Experimental

This project offers a sophisticated approach to developing intelligent agents that can learn complex tasks quickly within virtual environments, particularly in scenarios where data is scarce or the environment changes. It takes in observational data and desired outcomes from prior task executions to produce an agent capable of performing tasks more effectively through a novel 'external memory' mechanism. This is for researchers and developers working on advanced reinforcement learning and artificial intelligence, especially those in robotics, game AI, or simulation.

No commits in the last 6 months.

Use this if you are developing AI agents for complex, dynamic virtual environments and need them to learn efficiently from limited prior experience, similar to how humans use past knowledge.

Not ideal if you are looking for an out-of-the-box solution for simpler machine learning tasks, or if your primary focus is on classical supervised learning or basic reinforcement learning approaches.

reinforcement-learning-research intelligent-agent-development in-context-learning simulated-environments AI-robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

24

Forks

1

Language

Python

License

MIT

Last pushed

Oct 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ml-jku/RA-DT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.