Picture for Gugan Thoppe

Gugan Thoppe

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries

Mar 15, 2024
Figure 1 for Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
Figure 2 for Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
Viaarxiv icon

VaR\ and CVaR Estimation in a Markov Cost Process: Lower and Upper Bounds

Oct 17, 2023
Viaarxiv icon

Online Learning with Adversaries: A Differential Inclusion Analysis

Apr 04, 2023
Figure 1 for Online Learning with Adversaries: A Differential Inclusion Analysis
Viaarxiv icon

SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search

Jan 30, 2023
Figure 1 for SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
Figure 2 for SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
Figure 3 for SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
Figure 4 for SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
Viaarxiv icon

Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking

Add code
Aug 22, 2022
Figure 1 for Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking
Figure 2 for Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking
Figure 3 for Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking
Figure 4 for Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking
Viaarxiv icon

Approximate Q-learning and SARSA(0) under the $ε$-greedy Policy: a Differential Inclusion Analysis

May 26, 2022
Figure 1 for Approximate Q-learning and SARSA(0) under the $ε$-greedy Policy: a Differential Inclusion Analysis
Figure 2 for Approximate Q-learning and SARSA(0) under the $ε$-greedy Policy: a Differential Inclusion Analysis
Figure 3 for Approximate Q-learning and SARSA(0) under the $ε$-greedy Policy: a Differential Inclusion Analysis
Viaarxiv icon

A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning

Nov 10, 2021
Viaarxiv icon

Does Momentum Help? A Sample Complexity Analysis

Oct 29, 2021
Figure 1 for Does Momentum Help? A Sample Complexity Analysis
Figure 2 for Does Momentum Help? A Sample Complexity Analysis
Viaarxiv icon

Scale Invariant Solutions for Overdetermined Linear Systems with Applications to Reinforcement Learning

Apr 15, 2021
Figure 1 for Scale Invariant Solutions for Overdetermined Linear Systems with Applications to Reinforcement Learning
Figure 2 for Scale Invariant Solutions for Overdetermined Linear Systems with Applications to Reinforcement Learning
Figure 3 for Scale Invariant Solutions for Overdetermined Linear Systems with Applications to Reinforcement Learning
Figure 4 for Scale Invariant Solutions for Overdetermined Linear Systems with Applications to Reinforcement Learning
Viaarxiv icon

Online Algorithms for Estimating Change Rates of Web Pages

Sep 17, 2020
Figure 1 for Online Algorithms for Estimating Change Rates of Web Pages
Figure 2 for Online Algorithms for Estimating Change Rates of Web Pages
Figure 3 for Online Algorithms for Estimating Change Rates of Web Pages
Figure 4 for Online Algorithms for Estimating Change Rates of Web Pages
Viaarxiv icon