Task-agnostic Exploration in Reinforcement Learning
Xuezhou Zhang Yuzhe Ma Adish Singla
UW-Madison UW-Madison MPI-SWS
xzhang784@wisc.edu ma234@wisc.edu adishs@mpi-sws.org
Abstract
Efficient exploration is one of the main challenges in reinforcement learning (RL).
Most existing sample-efficient algorithms assume the existence of a single reward
function during exploration. In many practica ...


雷达卡


京公网安备 11010802022788号







