Fundamentals of Arthroscopic Surgery Training and beyond: a reinforcement learning exploration and benchmark
*International Journal of Computer Assisted Radiology and Surgery* · Ivan Ovinnikov, Ami Beuret, Flavia Cavaliere, Joachim M Buhmann
Ivan Ovinnikov
Applied Scientist · RL, Simulation & Physical AI
ANYbotics · Zürich, Switzerland
I connect research in inverse reinforcement learning, imitation learning, and robust objectives with deployed robot locomotion and scalable simulation workflows.
I completed my PhD at ETH Zürich on reinforcement learning from demonstrations in digital-twin simulations and now build RL locomotion systems for industrial quadruped robots at ANYbotics.
Selected work
Research that reaches real systems.
Deployed locomotion, simulation infrastructure, robust reward learning, and distributional objectives.
RL-Based Quadruped Locomotion Systems
Internal deployment work on RL locomotion controllers, sim-to-real training workflows, and safety-critical evaluation for industrial quadrupeds.
Causally Invariant Reward Learning
ArXiv preprint on reward learning from diverse demonstrations that remain stable under environment shifts.
FASTRL: Reinforcement Learning in Surgical Digital Twins
Peer-reviewed work on reinforcement-learning benchmarks and assistance policies in surgical digital-twin environments.
Sliced Wasserstein Imitation Learning
Turning optimal-transport distances between expert and policy behavior into practical reinforcement-learning rewards.
Hyperbolic Wasserstein Autoencoders
ArXiv preprint on generative modeling with Wasserstein autoencoders in hyperbolic latent spaces.
Selected publications
Papers and preprints.
Work spanning reinforcement learning, imitation learning, causal invariance, and optimal transport.
Details →
Imitation Learning using Generalized Sliced Wasserstein Distances
TMLR, in review · Ivan Ovinnikov, Alexander Terenin, Joachim M. Buhmann
Learning Causally Invariant Reward Functions from Diverse Demonstrations
Preprint / manuscript · Ivan Ovinnikov, Eugene Bykovets, Joachim M. Buhmann
Regularizing Adversarial Imitation Learning Using Causal Invariance
Preprint / manuscript · Ivan Ovinnikov, Joachim M. Buhmann
Poincare Wasserstein Autoencoder
Preprint / manuscript · Ivan Ovinnikov
Writing
Research notes and updates.
Research-grade applied ML for embodied agents
A short technical note on connecting reward learning, simulation-based training, and safety-critical evaluation for physical AI systems.
PhD examination
Successfully passed my PhD examination
FASTRL paper published in IJCARS
Our paper on surgical assistance agents in simulation was published in the