Reinforcement Learning · Reward Learning · Adaptive Training

Ivan Ovinnikov

Sequential decision-making under distribution shift.

Research on reinforcement learning, learning from demonstrations, and adaptive training distributions for robust, data-efficient decision-making.

ANYbotics · Zürich, Switzerland

Selected work Download CV

About

Researching how objectives and experience shape learning.

I am a machine learning researcher working on sequential decision-making under distribution shift. My research spans reinforcement learning, imitation and inverse reinforcement learning, reward learning, curriculum design, and risk-sensitive objectives.

A central theme of my work is that learning performance depends not only on the objective and model architecture, but also on the distribution of experience used for training. In interactive systems, this distribution is shaped by the current policy, the environment, the curriculum, and the failures selected for further learning. I develop methods for controlling these training and visitation distributions to improve robustness, data efficiency, and rare-event performance.

My work combines methodological research with evaluation in complex simulated and physical systems, including surgical digital twins and deployed quadruped locomotion.

Research areas

Adaptive training distributions

Curriculum, sampling, and replay methods that shape the learner’s experience using capability, uncertainty, learning progress, and failure risk.

Learning from demonstrations

Imitation, inverse reinforcement learning, and reward inference for problems where desired behaviour is easier to demonstrate than to specify directly.

Robust and risk-sensitive learning

Objectives and evaluation methods for distribution shift, reward misspecification, and low-probability but consequential failures.

Interactive model post-training

Applying reinforcement learning, reward learning, and adaptive experience generation to multimodal models and interactive agents.

Selected work

Methods, systems, and research artifacts.

Adaptive training, learning from demonstrations, reward design, and evaluation in simulated and physical systems.

Research artifact

RL-Based Quadruped Locomotion Systems

Internal deployment work on RL locomotion controllers, sim-to-real training workflows, and safety-critical evaluation for industrial quadrupeds.

Reinforcement LearningRoboticsSim-to-Real

Explore work Research artifact

Causally Invariant Reward Learning

Reward-model objective design from diverse demonstrations, with an invariance constraint intended to remain useful when the learned objective is optimized under distribution shift.

Imitation LearningReward LearningObjective Design

Explore work Research artifact