jangirrishabh/toyCarIRL

Implementation of Inverse Reinforcement Learning Algorithm on a toy car in a 2D world problem, (Apprenticeship Learning via Inverse Reinforcement Learning Abbeel & Ng, 2004)

48
/ 100
Emerging

This project helps developers understand the hidden motivations or 'reward functions' behind observed behaviors, specifically for autonomous agents like a toy car in a simulated 2D world. By observing an expert agent's movements and actions (trajectories), it estimates the underlying reward structure that drives that behavior. This tool is for researchers and developers working on creating intelligent systems that learn from demonstrations without explicit programming of rewards.

178 stars. No commits in the last 6 months.

Use this if you need to understand the goals or objectives of an observed expert behavior in a simulated environment to then replicate or modify it for an autonomous agent.

Not ideal if you already know the reward function for your agent or if your goal is simple behavioral cloning without inferring underlying intentions.

robotics-simulation autonomous-agents behavior-modeling machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

178

Forks

46

Language

Python

License

MIT

Last pushed

Oct 25, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jangirrishabh/toyCarIRL"

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