| Learning financial asset-specific trading rules via deep reinforcement learning M Taghian, A Asadi, R Safabakhsh Expert Systems with Applications 195, 116523, 2022 | 62 | 2022 |
| A reinforcement learning based encoder-decoder framework for learning stock trading rules M Taghian, A Asadi, R Safabakhsh arXiv preprint arXiv:2101.03867, 2021 | 8 | 2021 |
| Data-Aware compression of neural networks H Falahati, M Peyro, H Amini, M Taghian, M Sadrosadati, P Lotfi-Kamran, ... IEEE Computer Architecture Letters 20 (2), 94-97, 2021 | 3 | 2021 |
| Explainability of deep reinforcement learning algorithms in robotic domains by using Layer-wise Relevance Propagation M Taghian, S Miwa, Y Mitsuka, J Günther, S Golestan, O Zaiane Engineering Applications of Artificial Intelligence 137, 109131, 2024 | 1 | 2024 |
| Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms S Schoepp, M Taghian, S Miwa, Y Mitsuka, S Golestan, O Zaïane arXiv preprint arXiv:2407.15283, 2024 | | 2024 |
| General value functions for fault detection in multivariate time series data A Wong, M Taghian Jazi, T Takeuchi, J Günther, O Zaïane Frontiers in Robotics and AI 11, 1214043, 2024 | | 2024 |
| Representation Analysis of Deep Reinforcement Learning algorithms in Robotic Environments M Taghian Jazi | | 2022 |
Reza SafabakhshProfessor of Computer Engineering, Amirkabir University of TechnologyVerified email at aut.ac.ir
