Picture for Adithya M. Devraj

Adithya M. Devraj

Gaussian Imagination in Bandit Learning

Add code
Jan 30, 2022
Figure 1 for Gaussian Imagination in Bandit Learning
Viaarxiv icon

A Bit Better? Quantifying Information for Bandit Learning

Add code
Feb 18, 2021
Figure 1 for A Bit Better? Quantifying Information for Bandit Learning
Figure 2 for A Bit Better? Quantifying Information for Bandit Learning
Figure 3 for A Bit Better? Quantifying Information for Bandit Learning
Figure 4 for A Bit Better? Quantifying Information for Bandit Learning
Viaarxiv icon

Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning

Add code
Feb 24, 2020
Figure 1 for Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning
Figure 2 for Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning
Viaarxiv icon

Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic Approximation

Add code
Feb 07, 2020
Viaarxiv icon

Zap Q-Learning With Nonlinear Function Approximation

Add code
Oct 11, 2019
Figure 1 for Zap Q-Learning With Nonlinear Function Approximation
Figure 2 for Zap Q-Learning With Nonlinear Function Approximation
Viaarxiv icon

Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization

Add code
Jul 22, 2019
Figure 1 for Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization
Viaarxiv icon

Zap Q-Learning for Optimal Stopping Time Problems

Add code
May 01, 2019
Figure 1 for Zap Q-Learning for Optimal Stopping Time Problems
Viaarxiv icon

Differential Temporal Difference Learning

Add code
Dec 28, 2018
Figure 1 for Differential Temporal Difference Learning
Figure 2 for Differential Temporal Difference Learning
Figure 3 for Differential Temporal Difference Learning
Figure 4 for Differential Temporal Difference Learning
Viaarxiv icon

Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate

Add code
Sep 17, 2018
Figure 1 for Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate
Figure 2 for Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate
Figure 3 for Zap Meets Momentum: Stochastic Approximation Algorithms with Optimal Convergence Rate
Viaarxiv icon

Fastest Convergence for Q-learning

Add code
Mar 21, 2018
Figure 1 for Fastest Convergence for Q-learning
Figure 2 for Fastest Convergence for Q-learning
Figure 3 for Fastest Convergence for Q-learning
Figure 4 for Fastest Convergence for Q-learning
Viaarxiv icon