Mixline: A Hybrid Reinforcement Learning Framework for Long-horizon Bimanual Coffee Stirring Task.

Zheng Sun Zhiqi Wang Junjia Liu Miao Li Fei Chen

Published in: CoRR (2022)

Keyphrases

reinforcement learning
main contribution
probabilistic model
lightweight
genetic algorithm
artificial intelligence
information systems
multi agent
learning process
theoretical framework
markov decision processes