Avik Kar

activity

20232026

most citedFinite Time Regret Bounds for Minimum Variance Control of Autoregressive Systems with Exogenous Inputs

1 citations · 1 across the 5 of their papers we have counts for

collaborators

Showing 2026Show all

3 papers · 1 filter

cs.LG2026

$O (1/ n)$ Convergence Rate for RVI $Q$ -Learning

Avik Kar, Siddharth Chandak, Rahul Singh +1

We establish finite-time convergence guarantee for synchronous relative value iteration (RVI) $Q$ -learning for finite weakly communicating Markov decision processes (MDPs). For sto…

cs.LG2026

Policy Gradient Methods for Non-Markovian Reinforcement Learning

Avik Kar, Siddharth Chandak, Rahul Singh +4

We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To…

cs.LG2026

High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise

Avik Kar, Siddharth Chandak, Rahul Singh +3

We present the first uniform-in-time high-probability bound for SGD under the PL condition, where the gradient noise contains both Markovian and martingale difference components. T…

O(1/n) Convergence Rate for RVI Q-Learning

Policy Gradient Methods for Non-Markovian Reinforcement Learning

High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise

$O (1/ n)$ Convergence Rate for RVI $Q$ -Learning