MurpheyLab/inverse-mixed-strategy
(ICRA 2025) Inverse Mixed Strategy Games with Generative Trajectory Models
This project helps robotics researchers and engineers analyze complex, multi-robot interactions. It takes observed trajectories of multiple robots, even if the data is noisy, and infers the underlying decision-making strategies and potential risks or rewards influencing their movements. The output is a clear understanding of the robots' behavioral distributions, which can be used to predict future actions or design safer autonomous systems.
No commits in the last 6 months.
Use this if you need to understand the hidden motivations or strategies behind the observed movements of multiple interacting robots, especially in scenarios with imperfect data.
Not ideal if you are looking for a tool to directly control individual robot movements or to simulate simple, non-interactive robot paths.
Stars
17
Forks
2
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
May 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/MurpheyLab/inverse-mixed-strategy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.