Amir-massoud Farahmand

发表

Regularized Policy Iteration with Nonparametric Function Spaces

Shie Mannor, Csaba Szepesvári, Mohammad Ghavamzadeh, 2016, J. Mach. Learn. Res..

An implicit function learning approach for parametric modal regression pdf

Martha White, Amir-massoud Farahmand, Yangchen Pan, 2020, NeurIPS.

Value-Aware Loss Function for Model Learning in Reinforcement Learning

Csaba Szepesvari, Amir-massoud Farahmand, D. Nikovski, 2016 .

Reports of the AAAI 2014 Conference Workshops

Guy Van den Broeck, André da Motta Salles Barreto, Jenna Wiens, 2015, AI Mag..

CAPI : Generalized Classification-based Approximate Policy Iteration

Amir-massoud Farahmand, 2013 .

Classification-based Approximate Policy Iteration: Experiments and Extended Discussions pdf

André da Motta Salles Barreto, Doina Precup, Mohammad Ghavamzadeh, 2014, ArXiv.

Approximate MaxEnt Inverse Optimal Control

Amir-massoud Farahmand, J. Bagnell, De-An Huang, 2015 .

Dimensionality Reduction for Representing the Knowledge of Probabilistic Models

Raquel Urtasun, Richard S. Zemel, Jake Snell, 2018, International Conference on Learning Representations.

V ALUE G RADIENT WEIGHTED M ODEL -B ASED R EINFORCEMENT L EARNING

Amir-massoud Farahmand, Animesh Garg, C. Voelcker, 2022 .

Understanding and mitigating the limitations of prioritized experience replay

Mohsen Rohani, Hengshuai Yao, Amir-massoud Farahmand, 2020, UAI.

Operator Splitting Value Iteration

M. Ghavamzadeh, Amir-massoud Farahmand, Amin Rakhsha, 2022, NeurIPS.

The act of remembering: a study in partially observable reinforcement learning pdf

Sheila A. McIlraith, Amir-massoud Farahmand, Toryn Q. Klassen, 2020, ArXiv.

Policy-Aware Model Learning for Policy Gradient Methods

M. Ghavamzadeh, Amir-massoud Farahmand, Romina Abachi, 2020, ArXiv.

Adversarial Robustness through Regularization: A Second-Order Approach pdf

Avery Ma, Fartash Faghri, Amir-massoud Farahmand, 2020, ArXiv.

Deep reinforcement learning for partial differential equation control

Daniel Nikovski, Amir-massoud Farahmand, Saleh Nabi, 2017, 2017 American Control Conference (ACC).

Random Projection Filter Bank for Time Series Data

Daniel Nikovski, Amir-massoud Farahmand, Sepideh Pourazarm, 2017, NIPS.

Learning to regulate rolling ball motion

Devesh K. Jha, Daniel Nikovski, William Yerazunis, 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

Learning-based modular indirect adaptive control for a class of nonlinear systems

Meng Xia, Mouhacine Benosman, Amir-massoud Farahmand, 2015, 2016 American Control Conference (ACC).

Approximate MaxEnt Inverse Optimal Control and Its Application for Mental Simulation of Human Interactions

J. Andrew Bagnell, Kris M. Kitani, De-An Huang, 2015, AAAI.

Iterative Value-Aware Model Learning

Amir-massoud Farahmand, Amir-massoud Farahmand, 2018, NeurIPS.

Learning to control partial differential equations: Regularized Fitted Q-Iteration approach

Daniel Nikovski, Amir-massoud Farahmand, Saleh Nabi, 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

Frequency-based Search-control in Dyna pdf

Amir-massoud Farahmand, Jincheng Mei, Yangchen Pan, 2020, ICLR.

λ-AC: Learning latent decision-aware models for reinforcement learning in continuous state-spaces

Amir-massoud Farahmand, Igor Gilitschenski, C. Voelcker, 2023, ArXiv.

Learning from Limited Demonstrations

Joelle Pineau, Doina Precup, Beomjoon Kim, 2013, NIPS.

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Murat A. Erdogdu, Amir-massoud Farahmand, Tyler Kastner, 2023, ArXiv.

Value Gradient weighted Model-Based Reinforcement Learning

Amir-massoud Farahmand, Animesh Garg, C. Voelcker, 2022, International Conference on Learning Representations.

Hill Climbing on Value Estimates for Search-control in Dyna

Martha White, Hengshuai Yao, Amir-massoud Farahmand, 2019, IJCAI.

Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients

Amir-massoud Farahmand, A. Jepson, Mete Kemertas, 2023, ArXiv.

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

Amir-massoud Farahmand, Yangchen Pan, A. Ma, 2023, 2308.06703.

Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control

Martha White, Daniel Nikovski, Amir-massoud Farahmand, 2018, ICML.

Truncated Approximate Dynamic Programming with Task-Dependent Terminal Value

Daniel Nikovski, Yuji Igarashi, Hiroki Konaka, 2016, AAAI.

Learning Positive Functions in a Hilbert Space

Amir-massoud Farahmand, J. Bagnell, 2015 .

λ-AC: Learning latent decision-aware models for reinforcement learning in continuous state-spaces

Amir-massoud Farahmand, Igor Gilitschenski, C. Voelcker, 2023, ArXiv.

Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients

Amir-massoud Farahmand, A. Jepson, Mete Kemertas, 2023, ArXiv.

Improving Adversarial Transferability via Model Alignment

Amir-massoud Farahmand, Yangchen Pan, A. Ma, 2023, ArXiv.

Dissecting Deep RL with High Update Ratios: Combatting Value Overestimation and Divergence

Amir-massoud Farahmand, C. Voelcker, Marcel Hussing, 2024, ArXiv.

Value Gradient weighted Model-Based Reinforcement Learning

Amir-massoud Farahmand, Animesh Garg, C. Voelcker, 2022, International Conference on Learning Representations.

When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning

Amir-massoud Farahmand, C. Voelcker, Igor Gilitschenski, 2024, 2406.17718.

Maximum Entropy Model Correction in Reinforcement Learning

M. Ghavamzadeh, Amir-massoud Farahmand, Mete Kemertas, 2023, ArXiv.

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Murat A. Erdogdu, Amir-massoud Farahmand, Tyler Kastner, 2023, NeurIPS.

$\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models

Amir-massoud Farahmand, Igor Gilitschenski, C. Voelcker, 2023, 2306.17366.

Attentional Network for Visual Object Detection pdf

Ming-Yu Liu, Oncel Tuzel, Kota Hara, 2017, ArXiv.