Directory of Experts

Farahmand, Amir-Massoud

Directory of Experts

Farahmand, Amir-Massoud

Directory of Experts

Publications by type

Journal article (7) Conference paper (54) Book Book chapter Patent (1) Report Thesis (3) Dataset Teaching resource Image Audio recording Video recording Other

Amir Massoud Farahmand (65)

Journal articles (7)
- 2023
  - Ma, A., Pan, Y., & Farahmand, A.-M. (2023). Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods. Transactions on Machine Learning Research, 57 pages.
- 2019
  - Benosman, M., Farahmand, A.-M., & Xia, M. (2019). Learning-based iterative modular adaptive control for nonlinear systems. International Journal of Adaptive Control and Signal Processing, 33(2), 335-355.
- 2016
  - Farahmand, A.-M., Ghavamzadeh, M., Szepesvari, C., & Mannor, S. (2016). Regularized policy iteration with non parametric function spaces. Journal of Machine Learning Research, 17(139), 66 pages.
- 2015
  - Farahmand, A.-M., Precup, D., Barreto, A. M., & Ghavamzadeh, M. (2015). Classification-Based Approximate Policy Iteration. IEEE Transactions on Automatic Control, 60(11), 2989-2993.
- 2012
  - Farahmand, A.-M., & Szepesvári, C. (2012). Regularized least-squares regression: Learning from a β-mixing sequence. Journal of Statistical Planning and Inference, 142(2), 493-505.
- 2011
  - Farahmand, A.-M., & Szepesvári, C. (2011). Model selection in reinforcement learning. Machine Learning, 85(3), 299-332.
- 2010
  - Farahmand, A.-M., Ahmadabadi, M. N., Lucas, C., & Araabi, B. N. (2010). Interaction of Culture-Based Learning and Cooperative Co-Evolution and its Application to Automatic Behavior-Based System Design. IEEE Transactions on Evolutionary Computation, 14(1), 23-57.
Conference papers (54)
- 2025
  - Kemertas, M., Farahmand, A.-M., & Jepson, A. D. (2025, April). A truncated newton method for optimal transport [Paper]. 13th International Conference on Learning Representations (ICLR 2025), Singapore, Singapore.
- 2024
  - Pirmorad, E., Mansouri, F., & Farahmand, A.-M. (2024, December). Deep reinforcement learning for online control of stochastic partial differenctial equations [Paper]. 38th Conference on Neural Information Processing Systems (NeurIPS 2024), Vancouver, BC, Canada (6 pages).
  - Hussing, M., Voelcker, C. A., Gilitschenski, I., Farahmand, A.-M., & Eaton, E. (2024, August). Dissecting Deep RL with high update ratios : combatting value divergence [Paper]. Reinforcement Learning Conference (RLC 2024), Amherst, Massachusetts, USA (24 pages).
  - Ma, A., Farahmand, A.-M., Pan, Y., Torr, P., & Gu, J. (2024, September). Improving Adversarial Transferability via Model Alignment [Paper]. 18th European Conference on Computer Vision (ECCV 2024), Milan, Italy.
  - Rakhsha, A., Kemertas, M., Ghavamzadeh, M., & Farahmand, A.-M. (2024, May). Maximum entropy model correction in reinforcement learning [Presentation]. In 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria.
  - Bedaywi, M., Rakhsha, A., & Farahmand, A.-M. (2024, August). PID accelerated temporal difference algorithms [Paper]. Reinforcement Learning Conference (RLC 2024), Amherst, Massachusetts, USA (25 pages).
  - Voelcker, C. A., Kastner, T., Gilitschenski, I., & Farahmand, A.-M. (2024, August). When does self-prediction help? Understanding auxiliary tasks in reinforcement learning [Paper]. Reinforcement Learning Conference (RLC 2024), Amherst, Massachusetts, USA (31 pages).
- 2023
  - Kastner, T., Erdogdu, M. A., & Farahmand, A.-M. (2023, December). Distributional model equivalence for risk-sensitive reinforcement learning [Paper]. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, USA (22 pages).
- 2022
  - Liu, G., Adhikari, A. S., Farahmand, A.-M., & Poupart, P. (2022, April). Learning object-oriented dynamics for planning form text [Poster]. 10th International Conference on Learning Representations (ICLR 2022), En ligne / Online.
  - Rakhsha, A., Wang, A., Ghavamzadeh, M., & Farahmand, A.-M. (2022, December). Operator splitting value iteration [Presentation]. In 37th annual Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, Louisiana, USA (13 pages).
  - Pan, Y., Mei, J., Farahmand, A.-M., White, M., Yao, H., Rohani, M., & Luo, J. (2022, August). Understanding and mitigating the limitations of prioritized experience replay [Paper]. 38th Conference on Uncertainty in Artificial Intelligence (UIA 2022), Eindhoven, The Netherlands.
  - Voelcker, C. A., Liao, V., Garg, A., & Farahmand, A.-M. (2022, April). Value gradient weighted model-based reinforcement learning [Poster]. 10th International Conference on Learning Representations (ICLR 2022), En ligne / Online.
  - Abachi, R., Voelcker, C. A., Garg, A., & Farahmand, A.-M. (2022, July). VIPer : iterative value-aware model learning on the value improvement path [Paper]. Decision Awareness in Reinforcement Learning Workshop (DARL 2022), Baltimore, MD, USA (10 pages).
- 2021
  - Bedaywi, M., & Farahmand, A.-M. (2021, July). PID accelerated temporal difference algorithms [Paper]. 38th International Conference on Machine Learning (ICML 2021), En ligne / Online.
- 2020
  - Pan, Y., Imani, E., Farahmand, A.-M., & White, M. (2020, December). An implicit function learning approach for parametric modal regression [Paper]. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), En ligne / Online (11 pages).
  - Pan, Y., Mei, J., & Farahmand, A.-M. (2020, April). Frequency-based search-control in Dyna [Paper]. 8th International Conference on Learning Representations (ICLR 2020), En ligne / Online (21 pages).
- 2019
  - Law, M. T., Snell, J., Farahmand, A.-M., Urtasun, R., & Zemel, R. S. (2019, May). Dimensionality reduction for representing the knowledge of prababilistic models [Paper]. 7th International Conference on Learning Representations (ICLR 2019), New Orleans, Louisiana (34 pages).
  - Pan, Y., Yao, H., Farahmand, A.-M., & White, M. (2019, August). Hill climbing on value estimates for search-control in Dyna [Paper]. 28th International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China.
  - Akrout, M., Farahmand, A.-M., Jarmain, T., & Abid, L. (2019, October). Improving Skin Condition Classification with a Visual Symptom Checker Trained Using Reinforcement Learning [Paper]. 22nd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2019), Shenzhen, China.
  - Farahmand, A.-M. (2019, December). Value function in frequency domain and the characteristic value iteration algorithm [Paper]. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada (12 pages).
- 2018
  - Farahmand, A.-M. (2018, December). Iterative value-aware model learning [Paper]. 32th Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Qc, Canada (12 pages).
  - Pan, Y., Farahmand, A.-M., White, M., Nabi, S., Gover, P., & Nikovski, D. (2018, July). Reinforcement learning with function-valued action spaces for partial differential equation control [Paper]. 35th International Conference on Machine Learning (ICML 2018), Stockholm, Sweden.
- 2017
  - Farahmand, A.-M., Nabi, S., & Nikovski, D. N. (2017, May). Deep reinforcement learning for partial differential equation control [Paper]. American Control Conference (ACC 2017), Seattle, WA, USA.
  - Pourazarm, S., Farahmand, A.-M., & Nikovski, D. N. (2017, October). Fault detection and prognosis of time series data with random projection filter bank [Paper]. 9th annual Conference of the Prognostics and Health Management Society (PHM 2017), St. Petersburg, FL, USA (11 pages).
  - Farahmand, A.-M., Pourazarm, S., & Nikovski, D. N. (2017, December). Random projection filter bank for time series data [Paper]. 31st annual Conference on Neural Information Processing systsems (NeurIPS 2017), Long Beauch, CA, USA (11 pages).
  - Farahmand, A.-M., Barreto, A. M., & Nikovski, D. N. (2017, April). Value-aware loss function for model-based reinforcement learning [Paper]. 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Fort Lauderdale, FL, USA.
- 2016
  - Farahmand, A.-M. (2016, December). Iterative value-aware model learning [Presentation]. In 13th European Workshop on Reinforcement Learning (EWRL 2016), Barcelona, Spain.
  - Benosman, M., Farahmand, A.-M., & Xia, M. (2016, July). Learning-based modular indirect adaptive control for a class of nonlinear systems [Paper]. American Control Conference (ACC 2016), Boston, MA, USA.
  - Farahmand, A.-M., Nabi, S., Grover, P., & Nikovski, D. N. (2016, December). Learning to control partial differential equations: Regularized Fitted Q-Iteration approach [Paper]. 55th IEEE Conference on Decision and Control (CDC 2016), Las Vegas, NV, USA (8 pages).
  - Farahmand, A.-M., Nikovski, D. N., Igarashi, Y., & Konaka, H. (2016, February). Truncated approximate dynamic programming with task-dependent terminal value [Abstract]. 30th AAAI Conference on Artificial Intelligence (AAAI 2016), Phoenix, Arizona, USA.
  - Farahmand, A.-M. (2016, December). Value-aware loss function for model-based reinforcement learning [Paper]. 13th European Workshop on Reinforcement Learning (EWRL 2016), Barcelona, Spain (8 pages).
- 2015
  - Huang, D.-A., Farahmand, A.-M., Kitani, K. M., & Bagnell, J. A. (2015, June). Approximate MaxEnt inverse optimal control [Paper]. Reinforcement Learning and Decision Making (RLDM 2015), Edmonton, AB, CAnada (5 pages).
  - Huang, D.-A., Farahmand, A.-M., Kitani, K. M., & Bagnell, J. A. (2015, January). Approximate maxent inverse optimal control and its application for mental simulation of human interactions [Abstract]. 29th AAAI Conference on Artificial Intelligence (AAAI 2015), Austin, Texas, USA.
  - Bagnell, J. A., & Farahmand, A.-M. (2015, December). Learning positive functions in a Hilbert Space [Paper]. 8th NIPS Workshop on Optimization for Machine Learning (OPT 2015), Montreal, Qc, Canada (10 pages).
- 2014
  - Bachman, P., Farahmand, A.-M., & Precup, D. (2014, June). Sample-based approximate regularization [Paper]. 31st International Conference on Machine Learning (ICML 2014), Beijing, China (9 pages).
- 2013
  - Kim, B., Farahmand, A.-M., Pineau, J., & Precup, D. (2013, October). Approximate policy iteration with demonstrated data [Paper]. Multi-Disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton, NJ, USA.
  - Fard, M. M., Grinberg, Y., Farahmand, A.-M., Pineau, J., & Precup, D. (2013, December). Bellman error based feature generation using random projections on sparse spaces [Paper]. 27th Conference on Neural Information Processing Systems (NeurIPS 2013), Las Vegas, NV, USA (9 pages).
  - Farahmand, A.-M., Precup, D., Barreto, A. M. S., & Ghavamzadeh, M. (2013, October). CAPI : generalized classification-based approximate policy iteration [Paper]. Multi-Disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton, NJ, USA.
  - Kim, B., Farahmand, A.-M., Pineau, J., & Precup, D. (2013, December). Learning from limited demonstration [Paper]. 27th Conference on Neural Information Processing Systems (NeurIPS 2013), Las Vegas, NV, USA (9 pages).
- 2012
  - Farahmand, A.-M., & Precup, D. (2012, December). Value pursuit iteration [Paper]. 26th annual Conference on Neural Information Processing Systems (NeurIPS 2012), Lake Tahoe, Nevada, USA (9 pages).
- 2011
  - Farahmand, A.-M. (2011, December). Action-Gap phenomenon in reinforcement learning [Paper]. 25th annual Conference on Neural Information Processing Systems (NeurIPS 2011), Granada, Spain (9 pages).
- 2010
  - Farahmand, A.-M., Szepesvari, C., & Munos, R. (2010, December). Error propagation for approximate policy and value iteration [Paper]. 24th annual Conference on Neural Information Processing Systems (NeurIPS 2010), Vancouver, CB, Canada (9 pages).
  - Shademan, A., Farahmand, A.-M., & Jägersand, M. (2010, May). Robust Jacobian estimation for uncalibrated visual servoing [Paper]. IEEE International Conference on Robotics and Automation (ICRA 2010), Anchorage, AK, USA.
- 2009
  - Farahmand, A.-M., Shademan, A., Jägersand, M., & Szepesvári, C. (2009, May). Model-based and model-free reinforcement learning for visual servoing [Paper]. IEEE International Conference on Robotics and Automation, Kobe, Japan.
  - Farahmand, A.-M., Ghavamzadeh, M., Szepesvári, C., & Mannor, S. (2009, June). Regularized Fitted Q-Iteration for planning in continuous-space Markovian decision problems [Paper]. American Control Conference (ACC 2009), St. Louis, MO, USA.
  - Shademan, A., Farahmand, A.-M., & Jägersand, M. (2009, May). Towards Learning Robotic Reaching and Pointing: An Uncalibrated Visual Servoing Approach [Paper]. Canadian Conference on Computer and Robot Vision (CCRV 2009), Kelowna, BC, Canada.
- 2008
  - Farahmand, A.-M., Ghavamzadeh, M., Szepesvári, C., & Mannor, S. (2008, June). Regularized Fitted Q-Iteration: Application to Planning [Paper]. 8th European Workshop on Recent Advances in Reinforcement Learning (EWRL 2008), Villeneuve d'Ascq, France.
  - Farahmand, A.-M., Ghavamzadeh, M., Szepesvari, C., & Mannor, S. (2008, December). Regularized policy iteration [Paper]. 22th annual Conference on Neural Information Processing Systems (NeurIPS 2008), Vancouver, CB, Canada (8 pages).
- 2007
  - Farahmand, A.-M., Shademan, A., & Jägersand, M. (2007, October). Global visual-motor estimation for uncalibrated visual servoing [Paper]. IEEE/RSJ International Conference on Intelligent Robots and Systems, San Diego, CA, USA.
  - Farahmand, A.-M., Szepesvári, C., & Audibert, J.-Y. (2007, June). Manifold-adaptive dimension estimation [Paper]. 24th international conference on Machine learning (ICML 2007), Corvalis, Oregon, USA.
- 2006
  - Farahmand, A.-M., & Yazdanpanah, M. J. (2006, July). Channel Assignment using Chaotic Simulated Annealing Enhanced Hopfield Neural Network [Paper]. IEEE International Joint Conference on Neural Network Proceedings (IJCNN 2006), Vancouver, BC, Canada.
  - Azar, M. G., Ahmadabadi, M. N., Farahmand, A.-M., & Araabi, B. N. (2006, July). Learning to Coordinate Behaviors in Soft Behavior-Based Systems Using Reinforcement Learning [Paper]. IEEE International Joint Conference on Neural Network Proceedings (IJCNN 2006), Vancouver, BC, Canada.
- 2001
  - Farahmand, A.-M., Akhbari, R., & Tajvidi, M. (2001, March). Evolving hidden Markov models [Paper]. 4th Iranian Student Conference on Electrical Engineering (ISCEE 2001), Tehran, Iran.
- 2000
  - Farahmand, A.-M., & Mirmirani, E. (2000, January). Distributed genetic algorithms [Paper]. 3rd Iranian Student Conference on Electrical Engineering (ISCEE 2000), Tehran, Iran.
Patents (1)
- 2020
  - Nikovski, D. N., Zhu, Y., & Farahmand, A.-M. (2020). Methods and systems for discovery of prognostic subsequences in time series. (Patent no. US10712733).
Theses (3)
- 2011
  - Farahmand, A.-M. (2011). Regularization in reinforcement learning [Ph.D. Thesis, University of Alberta].
- 2005
  - Farahmand, A.-M. (2005). Learning and evolution in hierarchical behavior-based systems [Master's Thesis, University of Tehran].
- 2002
  - Farahmand, A.-M. (2002). Calculating resonant frequencies of a metallic cavity using finite element method [Master's Thesis, K.N. Toosi University of Technology].

Directory of Experts

Farahmand, Amir-Massoud

Directory of Experts

Farahmand, Amir-Massoud

You are here

Publications by type

Amir Massoud Farahmand (65)