New Approach in Human-AI Interaction by Reinforcement-Imitation Learning

Reinforcement Learning (RL) provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment states and action spaces, as well as in the determination of rewards. Imitation Learning (IL) offers a promising...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Neda Navidi, Rene Landry
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2021-03-01
Serija:	Applied Sciences
Teme:	reinforcement learning imitation learning human–AI collaboration
Online dostop:	https://www.mdpi.com/2076-3417/11/7/3068
Oznake:	Označite Brez oznak, prvi označite!