IRL-Toolkit
Runs inverse reinforcement learning experiments (e.g., GPIRL) in MATLAB to infer reward functions from demonstrated behavior.
- •You have trajectory data and need to uncover the underlying reward shaping for robotics or simulation.
- •You want to compare classic IRL algorithms (GPIRL, MaxEnt IRL) on a custom environment.
- •You need a MATLAB‑based reference implementation for research or prototyping before moving to production.
gpirl(states, actions, struct('kernel','rbf','lengthScale',1.0,'sigma_n',0.01,'maxIter',200));Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/irl-toolkit && curl -fsSL https://workflowstacks.com/api/skills/irl-toolkit/claude-skill -o ~/.claude/skills/irl-toolkit/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
IRL-Toolkit is a very large MATLAB project (~90k lines across 1048 code files, plus 7 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit 120 months ago, no license file, no tests found.
- 1README.txtStart here — what it does and how to install it
Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.
Expect 20–40 minutes in a terminal — or let your AI agent drive it.
mkdir -p ~/.claude/skills/irl-toolkit && curl -fsSL https://workflowstacks.com/api/skills/irl-toolkit/claude-skill -o ~/.claude/skills/irl-toolkit/SKILL.mdOpens the app with this repo with the prompt ready to go — no copy-paste needed.
Are you the creator of this tool? and earn 85% of every sale.
Show it off in your README:
[](https://workflowstacks.com/skills/irl-toolkit?utm_source=github&utm_medium=badge)The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.
Related skills
More ai-agent tools founders pair with this one.