Search Results for author:
Found 9 papers, 2 papers with code
Policy Mirror Descent with Lookahead
In this work, we propose a new class of PMD algorithms called $h$-PMD which incorporates multi-step greedy policy improvement with lookahead depth $h$ to the PMD update rule.
Independent Learning in Constrained Markov Potential Games
We propose an independent policy gradient algorithm for learning approximate constrained Nash equilibria: Each agent observes their own actions and rewards, along with a shared state.
Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence
Our main results are two-fold: (i) in the deterministic setting, we establish the first global last-iterate linear convergence result for the nested algorithm that seeks NE of zero-sum LQ games; (ii) in the model-free setting, we establish a~$\widetilde{\mathcal{O}}(\epsilon^{-2})$ sample complexity using a single-point ZO estimator.
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
We consider the reinforcement learning (RL) problem with general utilities which consists in maximizing a function of the state-action occupancy measure.
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
Recently, the impressive empirical success of policy gradient (PG) methods has catalyzed the development of their theoretical foundations.
Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation
Actor-critic methods integrating target networks have exhibited a stupendous empirical success in deep reinforcement learning.
Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Non Convex Optimization
In this work, we study the ADAM algorithm for smooth nonconvex optimization under a boundedness assumption on the adaptive learning rate.
Convergence Analysis of a Momentum Algorithm with Adaptive Step Size for Nonconvex Optimization
In this work, we study the algorithm for smooth nonconvex optimization under a boundedness assumption on the adaptive learning rate.
Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization
In the constant stepsize regime, assuming that the objective function is differentiable and non-convex, we establish the convergence in the long run of the iterates to a stationary point under a stability condition.
