Trajectory and episode log partners.
Offline RL, imitation learning, and evaluation all run on recorded episodes: the observations an agent saw, the actions it took, and what happened next. Well-labelled trajectories let a team start training before it has an environment, or compare a new policy against past behaviour.
We would work with you on a format Optimus can read directly, the labels that make a trajectory useful for a given task, and clear terms for how customers use it. Each dataset Optimus pulls in is recorded alongside the run's other artifacts, so it is always clear which data shaped which result.
How the trajectory and episode log partnership works
Steps
- 01
Share access
You give us access to the product, its technical documentation, and a contact on your engineering team.
- 02
We integrate
We build the integration and write the documentation Optimus follows, so it knows when to use your product and how.
- 03
Test together
We run it in a real training setup and check the results with you before anything reaches a customer.
- 04
Go live
Optimus can select your product in customer runs, on commercial terms we agree with you.
For researchers
If you study data quality, imitation learning, or learning from human feedback, we would like to work with you. Run studies with Optimus on your own datasets, compare how different data changes a trained model, and publish what you find. We are open to writing results up together.
Academic labs, independent researchers, and open-source teams can apply for up to $30,000 in Iacon credits through our research grants.
Talk to us
If a training run consumes what you sell, we should talk. Book a time directly, or write to dev@iaconautonomics.com and tell us which layer you supply.
Book a call