Kotb, M., Weber, C., Hafez, M. B., & Wermter, S. (2025). QT-TDM: Planning with Transformer Dynamics Model and Autoregressive Q-Learning. IEEE Robotics and Automation Letters (RA-L), vol. 10, no. 1, pp. 112-119. [PDF][Code]

Hafez, M. B., & Erekmen, K. (2024). Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation. Scientific Reports, 14(1), 31661. [PDF][Code]

Hafez, M. B., & Wermter, S. (2024). Continual Robot Learning using Self-Supervised Task Inference. IEEE Transactions on Cognitive and Developmental Systems (TCDS), vol. 16, no. 3, pp. 947-960. (Top-50 Most Popular and Frequently Accessed Documents in IEEE TCDS, Presented at the Journal Track of CoLLAs 2024). [PDF][Video][CoLLAs Presentation]

Hafez, M. B., Immisch, T., Weber, T., & Wermter, S. (2023). Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning. Frontiers in Neurorobotics, 17, 1127642. [Code]

Özdemir, O., Kerzel, M., Weber, C., Lee, J. H., Hafez, M. B., Bruns, P., & Wermter, S. (2023). Learning Bidirectional Action-Language Translation with Limited Supervision and Testing with Incongruent Input. Applied Artificial Intelligence, 37(1), 2179167. [PDF]

Hafez, M. B., Weber, C., Kerzel, M., & Wermter, S. (2020). Improving Robot Dual-System Motor Learning with Intrinsically Motivated Meta-Control and Latent-Space Experience Imagination. Robotics and Autonomous Systems, 133, 103630. [PDF][Code][Video]

Hafez, M. B., Weber, C., Kerzel, M., & Wermter, S. (2019). Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning. Paladyn, Journal of Behavioral Robotics, 10(1), 14–29. [PDF][Project][Video]

Sarip, A. G., Hafez, M. B., & Daud, M. N. (2016). Application of Fuzzy Regression Model for Real Estate Price Prediction. Malaysian Journal of Computer Science, 29(1), 15–27. [PDF]

Hafez, M. B., & Loo, C. K. (2015). Topological Q-learning with Internally Guided Exploration for Mobile Robot Navigation. Journal of Neural Computing and Applications, 26(8), 1939–1954. [PDF]

Sarip, A. G., & Hafez, M. B. (2015). Fuzzy Logic Application for House Price Prediction. International Journal of Property Sciences, 5(1), 24–30. [PDF] 

Zhao, X., Li., M., Weber, C., Hafez, M. B., & Wermter, S. (2023). Chat with the Environment: Interactive Multimodal Perception using Large Language Models. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 3590–3596. Detroit, Michigan, USA. (43% Acceptance Rate). [PDF][Code]

Zhao, X., Weber, C., Hafez, M. B., & Wermter, S. (2022). Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2512–2518. Kyoto, Japan. (48% Acceptance Rate). [PDF][Code]

Hafez, M. B., & Wermter, S. (2021). Behavior Self-Organization Supports Task Inference for Continual Robot Learning. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 6716–6723. Prague, Czech Republic. (45% Acceptance Rate). [PDF][Video]

Scholz, J., Weber, C., Hafez, M. B., & Wermter, S. (2021). Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 1–9. Virtual event. [PDF][Code]

Hafez, M. B., Weber, C., Kerzel, M., & Wermter, S. (2019). Efficient Intrinsically Motivated Robotic Grasping with Learning-Adaptive Imagination in Latent Space. Proceedings of the Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), 240–246. Oslo, Norway. [PDF][Project]

Hafez, M. B., Weber, C., Kerzel, M., & Wermter, S. (2019). Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 1–9. Budapest, Hungary. (Oral Presentation) (52.4% Acceptance Rate) [PDF][Project][Video]

Hafez, M. B., Kerzel, M. , Weber, C., & Wermter, S. (2018). Slowness-based neural visuomotor control with an Intrinsically motivated Continuous Actor-Critic. Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 509–514. Bruges, Belgium. (Oral Presentation) [PDF][Project]

Hafez, M. B., Weber, C., & Wermter, S. (2017). Curiosity-Driven Exploration Enhances Motor Skills of Continuous Actor-Critic Learner. Proceedings of the Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), 39–46. Lisbon, Portugal. [PDF][Project]

Hafez, M. B., & Loo, C. K. (2014). Curiosity-based Topological Reinforcement Learning. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), 1979–1984 . San Diego, CA, USA . [PDF]

Matthies, J., Hafez, M. B., Kotb, M., & Wermter, S. (2023). Model Predictive Control with Self-supervised Representation Learning. arXiv preprint arXiv: 2304.07219. [PDF][Code]