Search Results for author:
Found 12 papers, 1 papers with code
Gaussian Imagination in Bandit Learning
We study the performance of an agent that attains a bounded information ratio with respect to a bandit environment with a Gaussian prior distribution and a Gaussian likelihood function when applied instead to a Bernoulli bandit.
A Bit Better? Quantifying Information for Bandit Learning
The information ratio offers an approach to assessing the efficacy with which an agent balances between exploration and exploitation.
Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning
Sample complexity bounds are a common performance metric in the Reinforcement Learning literature.
Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic Approximation
This is motivation for the focus on mean square error bounds for parameter estimates.
Zap Q-Learning With Nonlinear Function Approximation
Based on multiple experiments with a range of neural network sizes, it is found that the new algorithms converge quickly and are robust to choice of function approximation architecture.
Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization
We consider a generic empirical composition optimization problem, where there are empirical averages present both outside and inside nonlinear loss functions.
Zap Q-Learning for Optimal Stopping Time Problems
The objective in this paper is to obtain fast converging reinforcement learning algorithms to approximate solutions to the problem of discounted cost optimal stopping in an irreducible, uniformly ergodic Markov chain, evolving on a compact subset of $\mathbb{R}^n$.
Differential Temporal Difference Learning
Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques.
Optimal Matrix Momentum Stochastic Approximation and Applications to Q-learning
There are two well known SA techniques that are known to have optimal asymptotic variance: the Ruppert-Polyak averaging technique, and stochastic Newton-Raphson (SNR).
Zap Q-Learning
The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins' original algorithm and recent competitors in several respects.
Fastest Convergence for Q-learning
The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins' original algorithm and recent competitors in several respects.
Differential TD Learning for Value Function Approximation
The algorithm introduced in this paper is intended to resolve two well-known problems with this approach: In the discounted-cost setting, the variance of the algorithm diverges as the discount factor approaches unity.
