Results 21 to 30 of about 17,478 (259)

Self-Imitation Learning

CoRR, 2018
This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration.
Junhyuk Oh, Yijie Guo, Satinder Singh 0001, Honglak Lee   +3 more
openaire   +3 more sources

Imitation of Peers in Children and Adults

Games, 2018
Imitation of the successful choices of others is a simple and superficially attractive learning rule. It has been shown to be an important driving force for the strategic behavior of (young) adults. In this study we examine whether imitation is prevalent
Jose Apesteguia, Steffen Huck, Jörg Oechssler, Elke Weidenholzer, Simon Weidenholzer   +4 more
doaj   +1 more source

The actions of others act as a pseudo-reward to drive imitation in the context of social reinforcement learning.

PLoS Biology, 2020
While there is no doubt that social signals affect human reinforcement learning, there is still no consensus about how this process is computationally implemented.
Anis Najar, Emmanuelle Bonnet, Bahador Bahrami, Stefano Palminteri   +3 more
doaj   +1 more source

Imitation Learning with Sinkhorn Distances

, 2023
Published as a conference paper at ECML PKDD ...
Papagiannis, Georgios, Li, Yunpeng
openaire   +3 more sources

Motion Generation Using Bilateral Control-Based Imitation Learning With Autoregressive Learning

IEEE Access, 2021
Imitation learning has been studied as an efficient and high-performance method to generate robot motion. Specifically, bilateral control-based imitation learning has been proposed as a method of realizing fast motion.
Ayumu Sasagawa, Sho Sakaino, Toshiaki Tsuji   +2 more
doaj   +1 more source

Imitation by Combination: Preschool Age Children Evidence Summative Imitation in a Novel Problem-Solving Task

Frontiers in Psychology, 2015
Children are exceptional, even ‘super’ imitators, but comparatively poor independent problem-solvers or innovators. However, human cultural evolution depends on both imitation and innovation.
Francys eSubiaul, Edward eKrajkowski, Elizabeth ePrice, Alexander eEtz   +3 more
doaj   +1 more source

Deep Reinforcement Learning Task Assignment Based on Domain Knowledge

IEEE Access, 2022
Deep Reinforcement Learning (DRL) methods are inefficient in the initial strategy exploration process due to the huge state space and action space in large-scale complex scenarios.
Jiayi Liu, Gang Wang, Xiangke Guo, Siyuan Wang, Qiang Fu   +4 more
doaj   +1 more source

Back to Reality for Imitation Learning

CoRR, 2021
Published at CoRL 2021, blue sky oral ...
openaire   +4 more sources

Neural Marker of Habituation at 5 Months of Age Associated with Deferred Imitation Performance at 12 Months: A Longitudinal Study in the UK and The Gambia

Children, 2022
Across cultures, imitation provides a crucial route to learning during infancy. However, neural predictors which would enable early identification of infants at risk of suboptimal developmental outcomes are still rare.
Laura Katus, Bosiljka Milosavljevic, Maria Rozhko, Samantha McCann, Luke Mason, Ebrima Mbye, Ebou Touray, Sophie E. Moore, Clare E. Elwell, Sarah Lloyd-Fox, Michelle de Haan, The BRIGHT Study Team   +11 more
doaj   +1 more source

Imitation learning and co-presence learning influence the acquisition of word formation rules: A fNIRS hyperscanning study

NeuroImage
Imitation learning and co-presence learning are common forms of social learning. However, the effects of these two types of learning on acquiring word formation rules have gone relatively underexplored, particularly in the context of adult social ...
Yujing Shen, Xiyuan Wang, John W. Schwieter, Huanhuan Liu   +3 more
doaj   +1 more source