18 citations · 23 across the 6 of their papers we have counts for
6 papers
Lie Group Algebra Convolutional Filters
Harshat Kumar, Alejandro Parada-Mayorga, Alejandro Ribeiro
In this paper we propose a framework to leverage Lie group symmetries on arbitrary spaces exploiting \textit{algebraic signal processing} (ASP). We show that traditional group conv…
Algebraic Convolutional Filters on Lie Group Algebras
Harshat Kumar, Alejandro Parada-Mayorga, Alejandro Ribeiro
Group convolutional neural networks are a useful tool for utilizing symmetries known to be in a signal; however, they require that the signal is defined on the group itself. Existi…
Parameter Critic: a Model Free Variance Reduction Method Through Imperishable Samples
Juan Cervino, Harshat Kumar, Alejandro Ribeiro
We consider the problem of finding a policy that maximizes an expected reward throughout the trajectory of an agent that interacts with an unknown environment. Frequently denoted R…
Zeroth-order Deterministic Policy Gradient
Harshat Kumar, Dionysios S. Kalogerias, George J. Pappas +1
Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling…
On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation
Harshat Kumar, Alec Koppel, Alejandro Ribeiro
Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine…
Navigation of a Quadratic Potential with Ellipsoidal Obstacles
Harshat Kumar, Santiago Paternain, Alejandro Ribeiro
Given a convex quadratic potential of which its minimum is the agent's goal and a Euclidean space populated with ellipsoidal obstacles, one can construct a Rimon-Koditschek (RK) ar…