Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · May 201819922001200920172026
3 results for “Greedy-GQ”
Finite-sample Analysis of Greedy-GQ with Linear Function Approximation under Markovian Noisecs.LG

Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.

problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.
reinforcement learningfinite-sample analysisGreedy-GQMarkovian noiseoptimal control
2020-05-20abs ↗pdf ↗
Sample Complexity Bounds for Two Timescale Value-based Reinforcement Learning Algorithmscs.LG

This paper analyzes the sample complexity of two timescale reinforcement learning algorithms.

problem Analyzing the sample complexity of two timescale reinforcement learning algorithms.
method Non-asymptotic analysis of linear and nonlinear TDC and Greedy-GQ algorithms under Markovian sampling with constant stepsize.
result The paper provides non-asymptotic convergence results for two timescale linear and nonlinear TDC and Greedy-GQ algorithms.
reinforcement learningtwo timescalesample complexitylinear TDCnonlinear TDC
2020-11-10abs ↗pdf ↗
Nonlinear Distributional Gradient Temporal-Difference Learningcs.LG

We devise a distributional variant of gradient temporal-difference (TD) learning. Distributional reinforcement learning has been demonstrated to outperform the regular one in the recent study \citep{bellemare2017distributional}. In the policy evaluation setting, we design two new algorithms called distributional GTD2 a…

2018-05-20abs ↗pdf ↗