Aritra Mitra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Aritra Mitra has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Robert Wendell Heath
Department of Electrical and Computer Engineering, University of California, San Diego, La Jolla, CA, USA
2 shared publications - Sreejeet Maity
North Carolina State University, Raleigh, USA
2 shared publications Arman Adibi
1 shared publicationAshwin Verma
1 shared publication- Ashwin Verma
Department of Electrical and Computer Engineering The Elmore Family School of Electrical and Computer Engineering The Elmore Family School of Electrical and Computer Engineering The Elmore Family School of Electrical and Computer Engineering Department of Electrical and Computer Engineering North Carolina State University Purdue University Purdue University Purdue University North Carolina State University
1 shared publication Chenyu Zhang
Data Science Institute Columbia University New York 10025 NY USA
1 shared publication
Latest Publications
- Open Access
- 9 October 2026
- Published by MDPI AG in Preprints.org
Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning
We study federated reinforcement learning in which multiple agents interact with a common Markov decision process and communicate through a central server to collaboratively learn the optimal stateaction value function. Our goal is to understand whether the sample-efficiency benefits of collaboration can be retained when a fraction of the agents behave adversarially and transmit arbitrarily corrupted information. To address this problem, we introduce Robust Async-Fed-Q, an epoch-based federated learning algorithm that combines variance-reduced estimation of the Bellman optimality operator at the agents with robust aggregation at the server. We establish high-probability finite-time guarantees showing that the proposed method preserves the statistical gains of collaboration among the honest agents while tolerating adversarial corruption. In particular, the effect of the adversarial agents decreases as the amount of data collected by each honest agent grows and eventually vanishes in the infinite-sample limit. We complement these guarantees with information-theoretic lower bounds that characterize the unavoidable statistical cost of adversarial corruption, leading to the first nearly matching upper and lower bounds for adversarially robust federated reinforcement learning. We further extend our framework to accommodate single-trajectory Markovian sampling and heterogeneous partial coverage, where different agents may explore different regions of the state-action space and learning relies on their collective coverage. Finally, our epoch-based design substantially improves the best known communication complexity for federated Q-learning under asynchronous sampling.
- 9 October 2026
- Published by MDPI AG in Preprints.org
Open AccessLearning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning
We study federated reinforcement learning in which multiple agents interact with a common Markov decision process and communicate through a central server to collaboratively learn the optimal stateaction value function. Our goal is to understand whether the sample-efficiency benefits of collaboration can be retained when a fraction of the agents behave adversarially and transmit arbitrarily corrupted information. To address this problem, we introduce Robust Async-Fed-Q, an epoch-based federated learning algorithm that combines variance-reduced estimation of the Bellman optimality operator at the agents with robust aggregation at the server. We establish high-probability finite-time guarantees showing that the proposed method preserves the statistical gains of collaboration among the honest agents while tolerating adversarial corruption. In particular, the effect of the adversarial agents decreases as the amount of data collected by each honest agent grows and eventually vanishes in the infinite-sample limit. We complement these guarantees with information-theoretic lower bounds that characterize the unavoidable statistical cost of adversarial corruption, leading to the first nearly matching upper and lower bounds for adversarially robust federated reinforcement learning. We further extend our framework to accommodate single-trajectory Markovian sampling and heterogeneous partial coverage, where different agents may explore different regions of the state-action space and learning relies on their collective coverage. Finally, our epoch-based design substantially improves the best known communication complexity for federated Q-learning under asynchronous sampling.
- Open Access
A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
Stochastic variance-reduced algorithms such as Stochastic Average Gradient (SAG) and SAGA, and their deterministic counterparts like the Incremental Aggregated Gradient (IAG) method, have been extensively studied in large-scale machine learning. Despite their popularity, existing analyses for these algorithms are disparate, relying on different proof techniques tailored to each method. Furthermore, the original proof of SAG is known to be notoriously involved, requiring computer-aided analysis. Focusing on finite-sum optimization with smooth and strongly convex objective functions, our main contribution is to develop a single unified convergence analysis that applies to all three algorithms: SAG, SAGA, and IAG. Our analysis features two key steps: (i) establishing a bound on delays due to stochastic sub-sampling using simple concentration tools, and (ii) carefully designing a novel Lyapunov function that accounts for such delays. The resulting proof is short and modular, providing the first high-probability bounds for SAG and SAGA that can be seamlessly extended to non-convex objectives and Markov sampling. As an immediate byproduct of our new analysis technique, we obtain the best known rates for the IAG algorithm, significantly improving upon prior bounds.
Open AccessA Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
Stochastic variance-reduced algorithms such as Stochastic Average Gradient (SAG) and SAGA, and their deterministic counterparts like the Incremental Aggregated Gradient (IAG) method, have been extensively studied in large-scale machine learning. Despite their popularity, existing analyses for these algorithms are disparate, relying on different proof techniques tailored to each method. Furthermore, the original proof of SAG is known to be notoriously involved, requiring computer-aided analysis. Focusing on finite-sum optimization with smooth and strongly convex objective functions, our main contribution is to develop a single unified convergence analysis that applies to all three algorithms: SAG, SAGA, and IAG. Our analysis features two key steps: (i) establishing a bound on delays due to stochastic sub-sampling using simple concentration tools, and (ii) carefully designing a novel Lyapunov function that accounts for such delays. The resulting proof is short and modular, providing the first high-probability bounds for SAG and SAGA that can be seamlessly extended to non-convex objectives and Markov sampling. As an immediate byproduct of our new analysis technique, we obtain the best known rates for the IAG algorithm, significantly improving upon prior bounds.
- Open Access
Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
It is known that reinforcement learning (RL) is data-hungry. To improve sample-efficiency of RL, it has been proposed that the learning algorithm utilize data from 'approximately similar' processes. However, since the process models are unknown, identifying which other processes are similar poses a challenge. In this work, we study this problem in the context of the benchmark Linear Quadratic Regulator (LQR) setting. Specifically, we consider a setting with multiple agents, each corresponding to a copy of a linear process to be controlled. The agents' local processes can be partitioned into clusters based on similarities in dynamics and tasks. Combining ideas from sequential elimination and zeroth-order policy optimization, we propose a new algorithm that performs simultaneous clustering and learning to output a personalized policy (controller) for each cluster. Under a suitable notion of cluster separation that captures differences in closed-loop performance across systems, we prove that our approach guarantees correct clustering with high probability. Furthermore, we show that the sub-optimality gap of the policy learned for each cluster scales inversely with the size of the cluster, with no additional bias, unlike in prior works on collaborative learning-based control. Our work is the first to reveal how clustering can be used in data-driven control to learn personalized policies that enjoy statistical gains from collaboration but do not suffer sub-optimality due to inclusion of data from dissimilar processes. From a distributed implementation perspective, our method is attractive as it incurs only a mild logarithmic communication overhead.
Open AccessHarnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
It is known that reinforcement learning (RL) is data-hungry. To improve sample-efficiency of RL, it has been proposed that the learning algorithm utilize data from 'approximately similar' processes. However, since the process models are unknown, identifying which other processes are similar poses a challenge. In this work, we study this problem in the context of the benchmark Linear Quadratic Regulator (LQR) setting. Specifically, we consider a setting with multiple agents, each corresponding to a copy of a linear process to be controlled. The agents' local processes can be partitioned into clusters based on similarities in dynamics and tasks. Combining ideas from sequential elimination and zeroth-order policy optimization, we propose a new algorithm that performs simultaneous clustering and learning to output a personalized policy (controller) for each cluster. Under a suitable notion of cluster separation that captures differences in closed-loop performance across systems, we prove that our approach guarantees correct clustering with high probability. Furthermore, we show that the sub-optimality gap of the policy learned for each cluster scales inversely with the size of the cluster, with no additional bias, unlike in prior works on collaborative learning-based control. Our work is the first to reveal how clustering can be used in data-driven control to learn personalized policies that enjoy statistical gains from collaboration but do not suffer sub-optimality due to inclusion of data from dissimilar processes. From a distributed implementation perspective, our method is attractive as it incurs only a mild logarithmic communication overhead.
- Open Access
Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
We consider the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting where the reward signal is subject to adversarial corruption. Such corruption, which may arise from extreme noise, sensor faults, or malicious attacks, can severely degrade the performance of classical algorithms such as Q-learning. To address this challenge, we propose a new provably robust variant of the Q-learning algorithm that operates effectively even when a fraction of the observed rewards are arbitrarily perturbed by an adversary. Under the asynchronous sampling model with time-correlated data, we establish that despite adversarial corruption, the finite-time convergence rate of our algorithm matches that of existing results for the non-adversarial case, up to an additive term proportional to the fraction of corrupted samples. Moreover, we derive an information-theoretic lower bound revealing that the additive corruption term in our upper bounds is unavoidable. Next, we propose a variant of our algorithm that requires no prior knowledge of the statistics of the true reward distributions. The analysis of this setting is particularly challenging and is enabled by carefully exploiting a refined Azuma-Hoeffding inequality for almost-martingales, a technical tool that might be of independent interest. Collectively, our contributions provide the first finite-time robustness guarantees for asynchronous Q-learning, bridging a significant gap in robust RL.
Open AccessCorruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
We consider the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting where the reward signal is subject to adversarial corruption. Such corruption, which may arise from extreme noise, sensor faults, or malicious attacks, can severely degrade the performance of classical algorithms such as Q-learning. To address this challenge, we propose a new provably robust variant of the Q-learning algorithm that operates effectively even when a fraction of the observed rewards are arbitrarily perturbed by an adversary. Under the asynchronous sampling model with time-correlated data, we establish that despite adversarial corruption, the finite-time convergence rate of our algorithm matches that of existing results for the non-adversarial case, up to an additive term proportional to the fraction of corrupted samples. Moreover, we derive an information-theoretic lower bound revealing that the additive corruption term in our upper bounds is unavoidable. Next, we propose a variant of our algorithm that requires no prior knowledge of the statistics of the true reward distributions. The analysis of this setting is particularly challenging and is enabled by carefully exploiting a refined Azuma-Hoeffding inequality for almost-martingales, a technical tool that might be of independent interest. Collectively, our contributions provide the first finite-time robustness guarantees for asynchronous Q-learning, bridging a significant gap in robust RL.
- Open Access
Power-Constrained Policy Gradient Methods for LQR
Consider a discrete-time Linear Quadratic Regulator (LQR) problem solved using policy gradient descent when the system matrices are unknown. The gradient is transmitted across a noisy channel over a finite time horizon using analog communication by a transmitter with an average power constraint. This is a simple setup at the intersection of reinforcement learning and networked control systems. We first consider a communication-constrained optimization framework, where gradient descent is applied to optimize a non-convex function under noisy gradient transmission. We provide an optimal power allocation algorithm that minimizes an upper bound on the expected optimality error at the final iteration and show that adaptive power allocation can lead to better convergence rate as compared to standard gradient descent with uniform power distribution. We then apply our results to the LQR setting.
Open AccessPower-Constrained Policy Gradient Methods for LQR
Consider a discrete-time Linear Quadratic Regulator (LQR) problem solved using policy gradient descent when the system matrices are unknown. The gradient is transmitted across a noisy channel over a finite time horizon using analog communication by a transmitter with an average power constraint. This is a simple setup at the intersection of reinforcement learning and networked control systems. We first consider a communication-constrained optimization framework, where gradient descent is applied to optimize a non-convex function under noisy gradient transmission. We provide an optimal power allocation algorithm that minimizes an upper bound on the expected optimality error at the final iteration and show that adaptive power allocation can lead to better convergence rate as compared to standard gradient descent with uniform power distribution. We then apply our results to the LQR setting.
- 4 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. PP (15361276) , 1
Finite-Time Analysis of Over-the-Air Federated TD Learning
In recent years, federated learning has been widely studied to speed up various supervised learning tasks at the wireless network edge. However, there is a lack of theoretical understanding as to whether similar speedups in sample complexity can be achieved for cooperative reinforcement learning (RL) problems subject to communication constraints. To that end, we study a federated policy evaluation problem over wireless fading channels where, to update model parameters, a central server aggregates local temporal difference (TD) update directions from N agents via analog over-the-air computation (OAC). We refer to this scheme as OAC-FedTD and provide a rigorous finite-time convergence analysis of its performance. Our analysis reveals the impact of the noisy fading channels on the convergence rate and establishes a linear convergence speedup w.r.t. the number of agents. Notably, this is the first non-asymptotic analysis of a cooperative RL setting under wireless channels that jointly considers linear value function approximation, Markovian sampling, and the OAC channel-induced distortions and noise. Our work develops the theoretical foundations that are key for relevant advancements in the analysis and design of federated reinforcement learning algorithms over wireless networks.
- 4 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. PP (15361276) , 1
Finite-Time Analysis of Over-the-Air Federated TD Learning
In recent years, federated learning has been widely studied to speed up various supervised learning tasks at the wireless network edge. However, there is a lack of theoretical understanding as to whether similar speedups in sample complexity can be achieved for cooperative reinforcement learning (RL) problems subject to communication constraints. To that end, we study a federated policy evaluation problem over wireless fading channels where, to update model parameters, a central server aggregates local temporal difference (TD) update directions from N agents via analog over-the-air computation (OAC). We refer to this scheme as OAC-FedTD and provide a rigorous finite-time convergence analysis of its performance. Our analysis reveals the impact of the noisy fading channels on the convergence rate and establishes a linear convergence speedup w.r.t. the number of agents. Notably, this is the first non-asymptotic analysis of a cooperative RL setting under wireless channels that jointly considers linear value function approximation, Markovian sampling, and the OAC channel-induced distortions and noise. Our work develops the theoretical foundations that are key for relevant advancements in the analysis and design of federated reinforcement learning algorithms over wireless networks.
- 27 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (2) , 1388-1394
A Simple Finite-Time Analysis of TD Learning With Linear Function Approximation
We study the finite-time convergence of temporal-difference (TD) learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in the algorithm to simplify the analysis, or require a fairly intricate argument to ensure stability of the iterates. We ask: Is it possible to retain the simplicity of a projection-based analysis without actually performing a projection step in the algorithm? Our main contribution is to show this is possible via a novel two-step argument. In the first step, we use induction to prove that under a standard choice of a constant step-size $\alpha$, the iterates generated by TD learning remain uniformly bounded in expectation. In the second step, we establish a recursion that mimics the steady-state dynamics of TD learning up to a bounded perturbation on the order of $O(\alpha ^{2})$ that captures the effect of Markovian sampling. Combining these pieces leads to an overall approach that considerably simplifies existing proofs. We conjecture that our inductive proof technique will find applications in the analyses of more complex stochastic approximation algorithms, and conclude by providing some examples of such applications.
- 27 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 70 (2) , 1388-1394
A Simple Finite-Time Analysis of TD Learning With Linear Function Approximation
We study the finite-time convergence of temporal-difference (TD) learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in the algorithm to simplify the analysis, or require a fairly intricate argument to ensure stability of the iterates. We ask: Is it possible to retain the simplicity of a projection-based analysis without actually performing a projection step in the algorithm? Our main contribution is to show this is possible via a novel two-step argument. In the first step, we use induction to prove that under a standard choice of a constant step-size $\alpha$, the iterates generated by TD learning remain uniformly bounded in expectation. In the second step, we establish a recursion that mimics the steady-state dynamics of TD learning up to a bounded perturbation on the order of $O(\alpha ^{2})$ that captures the effect of Markovian sampling. Combining these pieces leads to an overall approach that considerably simplifies existing proofs. We conjecture that our inductive proof technique will find applications in the analyses of more complex stochastic approximation algorithms, and conclude by providing some examples of such applications.
- Open Access
- 20 May 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Symposium Series
- Vol. 3 (1) , 308
Towards Robust Multi-Agent Reinforcement Learning
Stochastic gradient descent (SGD) is at the heart of large-scale distributed machine learning paradigms such as federated learning (FL). In these applications, the task of training high-dimensional weight vectors is distributed among several workers that exchange information over networks of limited bandwidth. While parallelization at such an immense scale helps to reduce the computational burden, it creates several other challenges: delays, asynchrony, and most importantly, a significant communication bottleneck. The popularity and success of SGD can be attributed in no small part to the fact that it is extremely robust to such deviations from ideal operating conditions. Inspired by these findings, we ask: Are common reinforcement learning (RL) algorithms also robust to similarly structured perturbations? Perhaps surprisingly, despite the recent surge of interest in multi-agent/federated RL, almost nothing is known about the above question. This paper collects some of our recent results in filling this void.
- 20 May 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Symposium Series
- Vol. 3 (1) , 308
Open AccessTowards Robust Multi-Agent Reinforcement Learning
Stochastic gradient descent (SGD) is at the heart of large-scale distributed machine learning paradigms such as federated learning (FL). In these applications, the task of training high-dimensional weight vectors is distributed among several workers that exchange information over networks of limited bandwidth. While parallelization at such an immense scale helps to reduce the computational burden, it creates several other challenges: delays, asynchrony, and most importantly, a significant communication bottleneck. The popularity and success of SGD can be attributed in no small part to the fact that it is extremely robust to such deviations from ideal operating conditions. Inspired by these findings, we ask: Are common reinforcement learning (RL) algorithms also robust to similarly structured perturbations? Perhaps surprisingly, despite the recent surge of interest in multi-agent/federated RL, almost nothing is known about the above question. This paper collects some of our recent results in filling this void.
- Open Access
Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward functions and transition kernels of the agents' MDPs, and continuous state-action spaces. Moreover, in the on-policy setting, the behavior policies vary with time, further complicating the analysis. In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis. Notably, we establish that FedSARSA converges to a policy that is near-optimal for all agents, with the extent of near-optimality proportional to the level of heterogeneity. Furthermore, we prove that FedSARSA leverages agent collaboration to enable linear speedups as the number of agents increases, which holds for both fixed and adaptive step-size configurations.
Open AccessFinite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward functions and transition kernels of the agents' MDPs, and continuous state-action spaces. Moreover, in the on-policy setting, the behavior policies vary with time, further complicating the analysis. In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis. Notably, we establish that FedSARSA converges to a policy that is near-optimal for all agents, with the extent of near-optimality proportional to the level of heterogeneity. Furthermore, we prove that FedSARSA leverages agent collaboration to enable linear speedups as the number of agents increases, which holds for both fixed and adaptive step-size configurations.
- Open Access
Min-Max Optimization under Delays
Delays and asynchrony are inevitable in large-scale machine-learning problems where communication plays a key role. As such, several works have extensively analyzed stochastic optimization with delayed gradients. However, as far as we are aware, no analogous theory is available for min-max optimization, a topic that has gained recent popularity due to applications in adversarial robustness, game theory, and reinforcement learning. Motivated by this gap, we examine the performance of standard min-max optimization algorithms with delayed gradient updates. First, we show (empirically) that even small delays can cause prominent algorithms like Extra-gradient (\texttt{EG}) to diverge on simple instances for which \texttt{EG} guarantees convergence in the absence of delays. Our empirical study thus suggests the need for a careful analysis of delayed versions of min-max optimization algorithms. Accordingly, under suitable technical assumptions, we prove that Gradient Descent-Ascent (\texttt{GDA}) and \texttt{EG} with delayed updates continue to guarantee convergence to saddle points for convex-concave and strongly convex-strongly concave settings. Our complexity bounds reveal, in a transparent manner, the slow-down in convergence caused by delays.
Open AccessMin-Max Optimization under Delays
Delays and asynchrony are inevitable in large-scale machine-learning problems where communication plays a key role. As such, several works have extensively analyzed stochastic optimization with delayed gradients. However, as far as we are aware, no analogous theory is available for min-max optimization, a topic that has gained recent popularity due to applications in adversarial robustness, game theory, and reinforcement learning. Motivated by this gap, we examine the performance of standard min-max optimization algorithms with delayed gradient updates. First, we show (empirically) that even small delays can cause prominent algorithms like Extra-gradient (\texttt{EG}) to diverge on simple instances for which \texttt{EG} guarantees convergence in the absence of delays. Our empirical study thus suggests the need for a careful analysis of delayed versions of min-max optimization algorithms. Accordingly, under suitable technical assumptions, we prove that Gradient Descent-Ascent (\texttt{GDA}) and \texttt{EG} with delayed updates continue to guarantee convergence to saddle points for convex-concave and strongly convex-strongly concave settings. Our complexity bounds reveal, in a transparent manner, the slow-down in convergence caused by delays.