Subgoal-Based Reward Shaping to Improve Efficiency in Reinforcement Learning

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge in real environments. Many studies have incorporated human k...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Takato Okudo, Seiji Yamada
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2021-01-01
Edice:	IEEE Access
Témata:	Reinforcement learning subgoals as human knowledge potential-based reward shaping reward shaping
On-line přístup:	https://ieeexplore.ieee.org/document/9459751/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!