13 citations · 25 across the 13 of their papers we have counts for
18 papers
Brittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systems
İbrahim Oğuz Çetinkaya, Sajad Khodadadian, Taylan Topcu
As systems engineering (SE) shifts from monolithic systems to Systems of Systems, Mission Engineering (ME) has emerged as a new line of thinking in SE. Mission environments are unc…
Deep Reinforcement Learning with Buffered Quantile Objectives
Mohammad Alipour-vaezi, Sajad Khodadadian
Quantile-based reinforcement learning provides an interpretable approach to risk-sensitive decision-making by optimizing a prescribed quantile of the cumulative-return distribution…
Risk-Sensitive Reinforcement Learning with Smoothed Quantile Objectives
Mohammad Alipour-Vaezi, Huaiyang Zhong, Sajad Khodadadian
Reinforcement Learning (RL) has achieved tremendous success in recent years. However, the classical foundations of RL do not account for the risk sensitivity of the objective funct…
Finite-Time Analysis of the Natural Policy Gradient in Finite-Horizon Markov Decision Processes
Asha Barua, Sajad Khodadadian
Natural Policy Gradient (NPG) is a well-established Reinforcement Learning algorithm that underlies widely used methods such as Trust Region Policy Optimization and Proximal Policy…
Leveraging High-Fidelity Digital Models and Reinforcement Learning for Mission Engineering: A Case Study of Aerial Firefighting Under Perfect Information
İbrahim Oğuz Çetinkaya, Sajad Khodadadian, Taylan G. Topcu
As systems engineering (SE) objectives evolve from design and operation of monolithic systems to complex System of Systems (SoS), the discipline of Mission Engineering (ME) has eme…
Optimistic Reinforcement Learning with Quantile Objectives
Mohammad Alipour-Vaezi, Huaiyang Zhong, Kwok-Leung Tsui +1
Reinforcement Learning (RL) has achieved tremendous success in recent years. However, the classical foundations of RL do not account for the risk sensitivity of the objective funct…
Tail Distribution of Regret in Optimistic Reinforcement Learning
Sajad Khodadadian, Mehrdad Moharrami
We derive instance-dependent tail bounds for the regret of optimism-based reinforcement learning in finite-horizon tabular Markov decision processes with unknown transition dynamic…
A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging
Sajad Khodadadian, Martin Zubeldia
Polyak-Ruppert averaging is a widely used technique to achieve the optimal asymptotic variance of stochastic approximation (SA) algorithms, yet its high-probability performance gua…
Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise
Shaan Ul Haque, Sajad Khodadadian, Siva Theja Maguluri
Stochastic approximation (SA) is an iterative algorithm for finding the fixed point of an operator using noisy samples and widely used in optimization and Reinforcement Learning (R…
Backward Curriculum Reinforcement Learning
KyungMin Ko
Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. Whil…
Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning
Sajad Khodadadian, Pranay Sharma, Gauri Joshi +1
Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling observations from the environment is usually split across multiple agents. However, tra…
Information Theoretic Measures for Fairness-aware Feature Selection
Sajad Khodadadian, Mohamed Nafea, AmirEmad Ghassami +1
Machine learning algorithms are increasingly used for consequential decision making regarding individuals based on their relevant features. Features that are relevant for accurate…
On the Linear convergence of Natural Policy Gradient Algorithm
Sajad Khodadadian, Prakirt Raj Jhunjhunwala, Sushil Mahavir Varma +1
Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods…
Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation
Zaiwei Chen, Sajad Khodadadian, Siva Theja Maguluri
In this paper, we develop a novel variant of off-policy natural actor-critic algorithm with linear function approximation and we establish a sample complexity of $\mathcal{O}(ε^{-3…
Impact of Data Processing on Fairness in Supervised Learning
Sajad Khodadadian, AmirEmad Ghassami, Negar Kiyavash
We study the impact of pre and post processing for reducing discrimination in data-driven decision makers. We first analyze the fundamental trade-off between fairness and accuracy…
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
Sajad Khodadadian, Zaiwei Chen, Siva Theja Maguluri
In this paper, we provide finite-sample convergence guarantees for an off-policy variant of the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we…
Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm
Sajad Khodadadian, Thinh T. Doan, Justin Romberg +1
Actor-critic style two-time-scale algorithms are one of the most popular methods in reinforcement learning, and have seen great empirical success. However, their performance is not…
Fairness in Supervised Learning: An Information Theoretic Approach
AmirEmad Ghassami, Sajad Khodadadian, Negar Kiyavash
Automated decision making systems are increasingly being used in real-world applications. In these systems for the most part, the decision rules are derived by minimizing the train…