Karam Daaboul

2 accepted papers

2023

Robotic Control Using Model Based Meta Adaption

Karam Daaboul, Joel Ikels, J. Marius Zöllner

ICRA 2023poster

In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior knowledge. Model-based meta-reinforcement learning combines reinforcement learning via world models with Meta Reinforcement Learning (MRL) for increased sample efficiency. However, adaption to unknown t…

Cited by 2 Source ↗code ↗Scholar ↗

2021

Safe Continuous Control with Constrained Model-Based Policy Optimization

Moritz A. Zanger, Karam Daaboul, J. Marius Zöllner

IROS 2021poster

The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic nature of the classic RL optimization objective. In contrast to the traditional RL objective, safe exploration considers…

Cited by 18 Source ↗Scholar ↗