1. Model-augmented Prioritized Experience Replay
Youngmin Oh1, Jinwoo Shin2, Eunho Yang2,3, Sung Ju Hwang2,31Samsung Advanced Institute of Technology
2 Korea Advanced Institute of Science and Technology
3 AITRICS
本文是PER( Prioritized Experience Replay)的改进,在进行优先级计算时,进一步考虑了对transition的评估,即称为模型增强(model- augment)的PER
– 2022.7.29
2. Learning Altruistic Behaviours in Reinforcement Learning without External Rewards
Tim Franzmeyer
University of Oxford
frtim@robots.ox.ac.uk
Mateusz Malinowski
DeepMind
mateuszm@google.com
Joao F. Henriques ˜
University of Oxford
joao@robots.ox.ac.uk