csmile-1006/ARP
Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)
This project helps reinforcement learning researchers and practitioners train AI agents more effectively, especially in complex virtual environments like games or simulations. It takes expert demonstrations (recorded actions and observations) and multimodal reward signals (like those from images or language) as input. The output is a trained agent that can perform tasks in new, unseen environments with greater adaptability. This is ideal for those developing AI agents for gaming, robotics simulation, or complex control tasks.
No commits in the last 6 months.
Use this if you need to train AI agents to adapt to varied and novel scenarios using visual or linguistic cues, particularly in environments where traditional reward functions are hard to define.
Not ideal if your AI agent's environment is simple and has a clear, easily definable numerical reward system without the need for complex visual or linguistic understanding.
Stars
33
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/csmile-1006/ARP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
raviq/Simultra
Multiagent hybrid simulator of road traffic in Qt/C++ and OpenStreetMap.
RickYang2016/Gut-Pursuit-Domain-in-Robotarium-ISR2022
"Game-theoretic utility tree for multi-robot cooperative pursuit strategy" Paper with Code for...
gunjanmimo/DRONE-CONTROLLER
Drone Controller Physics Unity3D