Mostafa Kotb — accepted AI-conference papers

2025

QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning

Mostafa Kotb, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter

RA-L 2025

Inspired by the success of the Transformer architecture in natural language processing and computer vision, we investigate the use of Transformers in Reinforcement Learning (RL), specifically in modeling the environment's dynamics using Transformer Dynamics Models (TDMs). We evaluate the capabilitie

Cited by 9 Source ↗Scholar ↗

2023

Sample-Efficient Real-Time Planning with Curiosity Cross-Entropy Method and Contrastive Learning

Mostafa Kotb, Cornelius Weber, Stefan Wermter

IROS 2023poster

Model-based reinforcement learning (MBRL) with real-time planning has shown great potential in locomotion and manipulation control tasks. However, the existing planning methods, such as the Cross-Entropy Method (CEM), do not scale well to complex high-dimensional environments. One of the key reasons…

Cited by 3 Source ↗code ↗Scholar ↗