3 papers
cs.LG2025
Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies
Jiaqi Chen, Ji Shi, Cansu Sancaktar +2
Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting…
cs.AI2025
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk +2
Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approache…
cs.CV2020
End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
Cansu Sancaktar, Marcel van Gerven, Pablo Lanillos
We present a pixel-based deep active inference algorithm (PixelAI) inspired by human body perception and action. Our algorithm combines the free-energy principle from neuroscience,…