Health AI Central
Share:
Peer-Reviewed Publication
Neural Netw2021;135115-126.March 1, 2021Journal Article

Modular deep reinforcement learning from reward and punishment for robot navigation.

Jiexin Wang1, Stefan Elfwing2, Eiji Uchibe3
1Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seikacho, Soraku-gun, Kyoto 619-0288, Japan. Electronic address: wang-j@atr.jp.
2ContextVision AB, Storgatan 24, 582 23 Linkoping, Sweden. Electronic address: stefan.elfwing@contextvision.se.
3Department of Brain Robot Interface, ATR Computational Neuroscience Laboratories, 2-2-2 Hikaridai, Seikacho, Soraku-gun, Kyoto 619-0288, Japan. Electronic address: uchibe@atr.jp.
PubMed DOI

Abstract

Modular Reinforcement Learning decomposes a monolithic task into several tasks with sub-goals and learns each one in parallel to solve the original problem. Such learning patterns can be traced in the brains of animals. Recent evidence in neuroscience shows that animals utilize separate systems for processing rewards and punishments, illuminating a different perspective for modularizing Reinforcem…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.