Andrii Zadaianchuk
Papers
2
Total Citations
12
H-Index
2
About
Andrii Zadaianchuk is a researcher advancing the frontiers of robot learning, with a focus on model-based reinforcement learning, world models, and imitation learning. His work addresses a critical challenge: enabling robots to build internal representations of their environment that are both accurate and actionable. In his highly cited 2020 paper, "A Real-Robot Dataset for Assessing Transferability of Learned Dynamics Models" (10 citations), Zadaianchuk provided a crucial benchmark for the community, highlighting the gap between simulated and real-world dynamics learning—a key bottleneck for deploying robots outside the lab. More recently, in "Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination" (2024), he introduced a novel framework that allows robots to use compositional world models to "imagine" and plan manipulation tasks, significantly improving the realism and effectiveness of imitation learning. By bridging the gap between abstract world models and concrete physical interaction, Zadaianchuk’s work is paving the way for robots that can learn and adapt more flexibly, directly impacting the future of autonomous manipulation and embodied AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2