Sadegh Talebi
Tenure Track Adjunkt
Machine Learning
Universitetsparken 1
2100 København Ø
- 2024
- Udgivet
Logarithmic regret in communicating MDPs: Leveraging known dynamics with bandits
Saber, H., Pesquerel, F., Maillard, O. & Talebi, Mohammad Sadegh, 2024, Proceedings of the 15th Asian Conference on Machine Learning. PMLR, s. 1167-1182 (Proceedings of Machine Learning Research, Bind 222).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
- E-pub ahead of print
Scaling Power Management in Cloud Data Centers: A Multi-Level Continuous-Time MDP Approach
Chitsaz, B., Khonsari, A., Moradian, M., Dadlani, A. & Talebi, Mohammad Sadegh, 2024, (E-pub ahead of print) I: IEEE Transactions on Services Computing. 12 s.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
- 2023
- Udgivet
Double Graph Attention Networks for Visual Semantic Navigation
Lyu, Y. & Talebi, Mohammad Sadegh, 2023, I: Neural Processing Letters. 55, 7, s. 9019-9040Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
- Udgivet
Exploration in Reward Machines with Low Regret
Bourel, Hippolyte Raymond, Jonsson, A., Maillard, O. A. & Talebi, Mohammad Sadegh, 2023, Proceedings of The 26th International Conference on Artificial Intelligence and Statistics. PMLR, Bind 206. s. 4114-4146 33 s. (Proceedings of Machine Learning Research, Bind 206).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
- Udgivet
Provably Efficient Offline Reinforcement Learning in Regular Decision Processes
Cipollone, R., Jonsson, A., Ronca, A. & Talebi, Mohammad Sadegh, 2023, Advances in Neural Information Processing Systems 36 (NeurIPS 2023). NeurIPS Proceedings, 34 s. (Advances in Neural Information Processing Systems, Bind 36).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
- Udgivet
Scaling Up Q-Learning via Exploiting State–Action Equivalence
Lyu, Y., Côme, A., Zhang, Y. & Talebi, Mohammad Sadegh, 2023, I: Entropy. 25, 4, 584.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
- 2022
- Udgivet
Bandit-Based Power Control in Full-Duplex Cooperative Relay Networks with Strict-Sense Stationary and Non-Stationary Wireless Communication Channels
Nomikos, N., Talebi, Mohammad Sadegh, Charalambous, T. & Wichman, R., 2022, I: IEEE Open Journal of the Communications Society. 3, s. 366-378 13 s.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
- 2021
- Udgivet
Improved Exploration in Factored Average-Reward MDPs
Talebi, Mohammad Sadegh, Jonsson, A. & Maillard, O., 2021, Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS). PMLR, s. 3988-3996 (Proceedings of Machine Learning Research, Bind 130).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
- 2020
- Udgivet
Adversarial Bandits with Corruptions
Yang, L., Hajiesmaili, M. H., Talebi, Mohammad Sadegh, Lui, J. C. S. & Wong, W. S., 2020, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtua. NeurIPS Proceedings, 10 s. (Advances in Neural Information Processing Systems, Bind 33).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
- Udgivet
Bandit-based relay selection in cooperative networks over unknown stationary channels
Nomikos, N., Talebi, Mohammad Sadegh, Wichman, R. & Charalambous, T., 2020, Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020. IEEE, 9231604Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
ID: 235125478
Flest downloads
-
51
downloads
Adversarial Bandits with Corruptions
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Udgivet -
41
downloads
Tightening Exploration in Upper Confidence Reinforcement Learning
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Udgivet -
22
downloads
Scaling Up Q-Learning via Exploiting State–Action Equivalence
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Udgivet