Early-Signal Detector

method · first seen 4 Oct 2026

maximum-entropy reinforcement learning

Also: SAC, ERRL, MaxEnt RL, soft Q-learning, soft actor-critic, soft reinforcement learning, entropy-regularized reinforcement learning

RL framework that augments reward with policy entropy to encourage exploration and robust stochastic policies.

Mentions per week

0719 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

control barrier functionKolmogorov-Arnold networkout-of-distribution generalizationhierarchical reinforcement learningLLM-based program evolutionzonotopeflow matchingone-step generative policydrifting generative modelsmean-field game