1 citations · 3 across the 13 of their papers we have counts for
16 papers
Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning
Sreejeet Maity, Aritra Mitra
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…
High-Probability Convergence of SGD via Batched Updates
Feng Zhu, Robert W. Heath, Aritra Mitra
Stochastic gradient descent (SGD) is the primary workhorse for large-scale optimization. While the average behavior of its iterates, typically characterized by mean-squared error b…
Robust Federated Q-Learning with Almost No Communication
Sreejeet Maity, Aritra Mitra
We consider a federated reinforcement learning setting involving agents, all of whom interact with a common Markov Decision Process (MDP). The agents exchange information via a…
Variance-Reduced Q-Learning over Static and Time-Varying Networks
Sreejeet Maity, Feng Zhu, Aritra Mitra +1
We investigate a decentralized reinforcement learning problem involving multiple agents that interact with the same Markov Decision Process (MDP). The agents can exchange informati…
Robust Asynchronous Q-Learning under Reward and State Corruption via Batching
Sreejeet Maity, Aritra Mitra
Motivated by reinforcement learning in harsh environments, we consider the problem of learning an optimal policy subject to adversarially corrupted feedback. Specifically, at each…
A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
Feng Zhu, Robert W. Heath, Aritra Mitra
Stochastic variance-reduced algorithms such as Stochastic Average Gradient (SAG) and SAGA, and their deterministic counterparts like the Incremental Aggregated Gradient (IAG) metho…
Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
Sreejeet Maity, Aritra Mitra
We study the problem of learning the optimal policy in a discounted, infinite-horizon reinforcement learning (RL) setting in the presence of adversarially corrupted rewards. To add…
Boosting-Enabled Robust System Identification of Partially Observed LTI Systems Under Heavy-Tailed Noise
Vinay Kanakeri, Aritra Mitra
We consider the problem of system identification of partially observed linear time-invariant (LTI) systems. Given input-output data, we provide non-asymptotic guarantees for identi…
Achieving Tighter Finite-Time Rates for Heterogeneous Federated Stochastic Approximation under Markovian Sampling
Feng Zhu, Aritra Mitra, Robert W. Heath
Motivated by collaborative reinforcement learning (RL) and optimization with time-correlated data, we study a generic federated stochastic approximation problem involving agent…
Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits
Sreejeet Maity, Aritra Mitra
One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. Th…
Outlier-Robust Linear System Identification Under Heavy-tailed Noise
Vinay Kanakeri, Aritra Mitra
We consider the problem of estimating the state transition matrix of a linear time-invariant (LTI) system, given access to multiple independent trajectories sampled from the system…
Towards Fast Rates for Federated and Multi-Task Reinforcement Learning
Feng Zhu, Robert W. Heath, Aritra Mitra
We consider a setting involving agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents' MDPs differ in their reward funct…
Robust Q-Learning under Corrupted Rewards
Sreejeet Maity, Aritra Mitra
Recently, there has been a surge of interest in analyzing the non-asymptotic behavior of model-free reinforcement learning algorithms. However, the performance of such algorithms i…
Finite-Time Analysis of Asynchronous Multi-Agent TD Learning
Nicolò Dal Fabbro, Arman Adibi, Aritra Mitra +1
Recent research endeavours have theoretically shown the beneficial effect of cooperation in multi-agent reinforcement learning (MARL). In a setting involving agents, this benef…
A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation
Aritra Mitra
We study the finite-time convergence of TD learning with linear function approximation under Markovian sampling. Existing proofs for this setting either assume a projection step in…
Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
Chenyu Zhang, Han Wang, Aritra Mitra +1
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from differe…