Search Results for author:
Found 13 papers, 0 papers with code
Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
Federated Reinforcement Learning (FRL) allows multiple agents to collaboratively build a decision making policy without sharing raw trajectories.
Risk Estimation in a Markov Cost Process: Lower and Upper Bounds
To the best of our knowledge, our work is the first to provide lower and upper bounds for estimating any risk measure beyond the mean within a Markovian setting.
Online Learning with Adversaries: A Differential-Inclusion Analysis
Our main result is that the proposed algorithm almost surely converges to the desired mean $\mu.$ This makes ours the first asynchronous FL method to have an a. s. convergence guarantee in the presence of adversaries.
SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search
We prove that the resulting variance decays exponentially with the planning horizon as a function of the expansion policy.
Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking
This leads to a lot of wasteful interactions since, once the ranking is done, only the data associated with the top-ranked policies is used for subsequent learning.
Demystifying Approximate Value-based RL with $ε$-greedy Exploration: A Differential Inclusion View
Q-learning and SARSA with $\epsilon$-greedy exploration are leading reinforcement learning methods.
Does Momentum Help? A Sample Complexity Analysis
Stochastic Heavy Ball (SHB) and Nesterov's Accelerated Stochastic Gradient (ASG) are popular momentum methods in stochastic optimization.
A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning
In Multi-Agent Reinforcement Learning (MARL), multiple agents interact with a common environment, as also with each other, for solving a shared problem in sequential decision-making.
Online Algorithms for Estimating Change Rates of Web Pages
We provide three novel schemes for online estimation of page change rates, all of which have extremely low running times per iteration.
Change Rate Estimation and Optimal Freshness in Web Page Crawling
Specifically, we provide two novel schemes for online estimation of page change rates.
A Tale of Two-Timescale Reinforcement Learning with the Tightest Finite-Time Bound
Algorithms such as these have two iterates, $\theta_n$ and $w_n,$ which are updated using two distinct stepsize sequences, $\alpha_n$ and $\beta_n,$ respectively.
Finite Sample Analyses for TD(0) with Function Approximation
TD(0) is one of the most commonly used algorithms in reinforcement learning.
Finite Sample Analysis of Two-Timescale Stochastic Approximation with Applications to Reinforcement Learning
Using this, we provide a concentration bound, which is the first such result for a two-timescale SA.
