633 citations · 1.5k across the 68 of their papers we have counts for
6 papers · 1 filter
Improved Algorithms for Misspecified Linear Markov Decision Processes
Daniel Vial, Advait Parulekar, Sanjay Shakkottai +1
For the misspecified linear Markov decision process (MLMDP) model of Jin et al. [2020], we propose an algorithm with three desirable properties. (P1) Its regret after episodes…
The Role of Lookahead and Approximate Policy Evaluation in Reinforcement Learning with Linear Value Function Approximation
Anna Winnicki, Joseph Lubars, Michael Livesay +1
Function approximation is widely used in reinforcement learning to handle the computational difficulties associated with very large state spaces. However, function approximation in…
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
Semih Cayci, Niao He, R. Srikant
Natural policy gradient (NPG) methods with entropy regularization achieve impressive empirical success in reinforcement learning problems with large state-action spaces. However, t…
The Dynamics of Gradient Descent for Overparametrized Neural Networks
Siddhartha Satpathi, R Srikant
We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under som…
Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
Daniel Vial, Advait Parulekar, Sanjay Shakkottai +1
We propose an algorithm that uses linear function approximation (LFA) for stochastic shortest path (SSP). Under minimal assumptions, it obtains sublinear regret, is computationally…
On Concentration Inequalities for Vector-Valued Lipschitz Functions
Dimitrios Katselis, Xiaotian Xie, Carolyn L. Beck +1
We derive two upper bounds for the probability of deviation of a vector-valued Lipschitz function of a collection of random variables from its expected value. The resulting upper b…