9 citations · 22 across the 11 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022
Build generally reusable agent-environment interaction models
Jun Jin, Hongming Zhang, Jun Luo
This paper tackles the problem of how to pre-train a model and make it generally reusable backbones for downstream task learning. In pre-training, we propose a method that builds a…
cs.LG2020★ 2 cited
LISPR: An Options Framework for Policy Reuse with Reinforcement Learning
Daniel Graves, Jun Jin, Jun Luo
We propose a framework for transferring any existing policy from a potentially unknown source MDP to a target MDP. This framework (1) enables reuse in the target domain of any form…
cs.LG2020★ 9 cited
Learning predictive representations in autonomous driving to improve deep reinforcement learning
Daniel Graves, Nhat M. Nguyen, Kimia Hassanzadeh +1
Reinforcement learning using a novel predictive representation is applied to autonomous driving to accomplish the task of driving between lane markings where substantial benefits i…