Muhammad Burhan Hafez

33 papers A 3B 4Journal 23Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition. IEEE Robotics Autom. Lett. Emily Miller, Michael Milford, Muhammad Burhan Hafez, Sarvapali D. Ramchurn, Shoaib Ehsan
2025	J	`jnl`	QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning. IEEE Robotics Autom. Lett. Mostafa Kotb, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2025	J	`jnl`	Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition. CoRR Emily Miller, Michael Milford, Muhammad Burhan Hafez, Sarvapali D. Ramchurn, Shoaib Ehsan
2024	J	`jnl`	Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation. CoRR Muhammad Burhan Hafez, Kerim Erekmen
2024	J	`jnl`	Continual Robot Learning Using Self-Supervised Task Inference. IEEE Trans. Cogn. Dev. Syst. Muhammad Burhan Hafez, Stefan Wermter
2024	J	`jnl`	QT-TDM: Planning with Transformer Dynamics Model and Autoregressive Q-Learning. CoRR Mostafa Kotb, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2023	A	`conf`	Chat with the Environment: Interactive Multimodal Perception Using Large Language Models. IROS Xufeng Zhao, Mengdi Li, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2023	J	`jnl`	Chat with the Environment: Interactive Multimodal Perception using Large Language Models. CoRR Xufeng Zhao, Mengdi Li, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2023	J	`jnl`	Continual Robot Learning using Self-Supervised Task Inference. CoRR Muhammad Burhan Hafez, Stefan Wermter
2023	J	`jnl`	Learning Bidirectional Action-Language Translation with Limited Supervision and Incongruent Extra Input. CoRR Ozan Özdemir, Matthias Kerzel, Cornelius Weber, Jae Hee Lee, Muhammad Burhan Hafez, Patrick Bruns, Stefan Wermter
2023	J	`jnl`	Learning Bidirectional Action-Language Translation with Limited Supervision and Testing with Incongruent Input. Appl. Artif. Intell. Ozan Özdemir, Matthias Kerzel, Cornelius Weber, Jae Hee Lee, Muhammad Burhan Hafez, Patrick Bruns, Stefan Wermter
2023	J	`jnl`	Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning. CoRR Muhammad Burhan Hafez, Tilman Immisch, Tom Weber, Stefan Wermter
2023	J	`jnl`	Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning. Frontiers Neurorobotics Muhammad Burhan Hafez, Tilman Immisch, Tom Weber, Stefan Wermter
2023	J	`jnl`	Model Predictive Control with Self-supervised Representation Learning. CoRR Jonas Matthies, Muhammad Burhan Hafez, Mostafa Kotb, Stefan Wermter
2022	A	`conf`	Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations. IROS Xufeng Zhao, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2022	J	`jnl`	Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations. CoRR Xufeng Zhao, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2021	A	`conf`	Behavior Self-Organization Supports Task Inference for Continual Robot Learning. IROS Muhammad Burhan Hafez, Stefan Wermter
2021	J	`jnl`	Behavior Self-Organization Supports Task Inference for Continual Robot Learning. CoRR Muhammad Burhan Hafez, Stefan Wermter
2021	B	`conf`	Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision. IJCNN Julien Scholz, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2021	J	`jnl`	Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision. CoRR Julien Scholz, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter
2020	J	`jnl`	Improving Robot Dual-System Motor Learning with Intrinsically Motivated Meta-Control and Latent-Space Experience Imagination. CoRR Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2020	J	`jnl`	Improving robot dual-system motor learning with intrinsically motivated meta-control and latent-space experience imagination. Robotics Auton. Syst. Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2020	—	`—`	Intrinsically Motivated Actor-Critic for Robot Motor Learning (Intrinsisch motivierter Akteur-Kritiker für Roboter-Lernen) Muhammad Burhan Hafez
2019	B	`conf`	Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning. IJCNN Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2019	J	`jnl`	Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning. CoRR Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2019	J	`jnl`	Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning. Paladyn J. Behav. Robotics Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2019	—	`conf`	Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space. ICDL-EPIROB Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2019	J	`jnl`	Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space. CoRR Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2018	J	`jnl`	Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning. CoRR Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter
2018	B	`conf`	Slowness-based neural visuomotor control with an Intrinsically motivated Continuous Actor-Critic. ESANN Muhammad Burhan Hafez, Matthias Kerzel, Cornelius Weber, Stefan Wermter
2017	—	`conf`	Curiosity-driven exploration enhances motor skills of continuous actor-critic learner. ICDL-EPIROB Muhammad Burhan Hafez, Cornelius Weber, Stefan Wermter
2015	J	`jnl`	Topological Q-learning with internally guided exploration for mobile robot navigation. Neural Comput. Appl. Muhammad Burhan Hafez, Chu Kiong Loo
2014	B	`conf`	Curiosity-based topological reinforcement learning. SMC Muhammad Burhan Hafez, Chu Kiong Loo