What does this research mean for the field?

A decision-theoretic approach to the discount factor in reinforcement learning provides an alternative framework to traditional fixed discount factor methods for Markov decision processes. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

July 17, 2019

Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach

Puntos clave

Los puntos clave no están disponibles para este artículo en este momento.

Resumen

Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor γ

Preguntar a la IA

Me gusta

Guardar

Cite This Study

Silviu Pitis (Wed,) studied this question.

synapsesocial.com/papers/6a24c97fa0f0424814279e75 https://doi.org/https://doi.org/10.1609/aaai.v33i01.33017949

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1A Markovian Decision Process1957 · 2,395 citations
2Time Discounting and Time Preference: A Critical Review2002 · 4,016 citations
3The Theory of Games and Economic Behavior1945 · 5,264 citations
4Reinforcement Learning: An Introduction2005 · 25,790 citations
5Rational Choice and the Framing of Decisions1986 · 3,613 citations

Preguntar a la IA

Me gusta

Guardar