Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

Softmax policy gradient with linear function approximation

technology1 mentionslast seen Oct 2, 2026

A policy gradient method with linear function approximation for multi-armed bandits, denoted Lin-SPG.

Relationships 2

Softmax policy gradient with linear function approximationdepends onlinear function approximation90% confidence1 source
Softmax policy gradient with linear function approximationapplies toreinforcement learning80% confidence1 source

Softmax policy gradient with linear function approximation

Relationship

Softmax policy gradient with linear function approximationapplies toreinforcement learning

80% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivOct 1, 2026Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits
Softmax PG with linear function approximation (referred to as $\texttt{Lin-SPG}$) and demonstrate that the approximation error is irrelevant to the algorithm's global convergence even in the bandit setting