Mohammadhossein Malmir
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohammadhossein Malmir has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Alois Knoll
Technical University of Munich
1 shared publication - Josip Josifovski
Technical University of Munich
1 shared publication - Noah Klarmann
Rosenheim Technical University of Applied Sciences
1 shared publication
Latest Publications
- Open Access
- 1 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (2) , 1037-1043
DiAReL: Reinforcement Learning With Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control
Delayed Markov decision processes (DMDPs) fulfill the Markov property by augmenting the state space of agents with a finite time window of recently committed actions. In reliance on these state augmentations, delay-resolved reinforcement learning (RL) algorithms train policies to learn optimal interactions with environments featuring observation or action delays. Although such methods can be directly trained on the real robots, due to sample inefficiency, limited resources, or safety constraints, a common approach is to transfer models trained in simulation to the physical robot. However, robotic simulations rely on approximated models of the physical systems, which hinders the sim2real transfer. In this work, we consider various uncertainties in modeling the robot or environment dynamics as unknown intrinsic disturbances applied to the system input. We introduce the disturbance-augmented Markov decision process (DAMDP) in delayed settings as a novel representation to incorporate disturbance estimation in training on-policy RL algorithms. The proposed method is validated across several metrics on learning robotic reaching and pushing tasks and compared with disturbance-unaware baselines. The results show that the disturbance-augmented models can achieve higher stabilization and robustness in the control response, which in turn improves the prospects of successful sim2real transfer.
- 1 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 34 (2) , 1037-1043
Open AccessDiAReL: Reinforcement Learning With Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control
Delayed Markov decision processes (DMDPs) fulfill the Markov property by augmenting the state space of agents with a finite time window of recently committed actions. In reliance on these state augmentations, delay-resolved reinforcement learning (RL) algorithms train policies to learn optimal interactions with environments featuring observation or action delays. Although such methods can be directly trained on the real robots, due to sample inefficiency, limited resources, or safety constraints, a common approach is to transfer models trained in simulation to the physical robot. However, robotic simulations rely on approximated models of the physical systems, which hinders the sim2real transfer. In this work, we consider various uncertainties in modeling the robot or environment dynamics as unknown intrinsic disturbances applied to the system input. We introduce the disturbance-augmented Markov decision process (DAMDP) in delayed settings as a novel representation to incorporate disturbance estimation in training on-policy RL algorithms. The proposed method is validated across several metrics on learning robotic reaching and pushing tasks and compared with disturbance-unaware baselines. The results show that the disturbance-augmented models can achieve higher stabilization and robustness in the control response, which in turn improves the prospects of successful sim2real transfer.