Avancerad sökning

Hittade 1 uppsats som matchar ovanstående sökkriterier.

1. 1. Minimal Exploration in Episodic Reinforcement Learning

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ardhendu Shekhar Tripathi; [2018]
   Nyckelord :Reinforcemebt Learning; Exploitation; Exploration; Regret; Optimism in Face of Uncertainty; Bayesian;

   Sammanfattning : Exploration-exploitation trade-off is a fundamental dilemma that reinforcement learning algorithms face. This dilemma is also central to the design of various state of the art bandit algorithms. We take inspiration from these algorithms and try to design reinforcement learning algorithms in an episodic setting. LÄS MER