A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
This paper considers the application of reinforcement learning to path nding tasks in continuous state space in the presence of obstacles. We show that cumulative evaluation functions (as Q-Functions 28] and V-Functions 4]) may be discontinuous if forbidden regions (as implied by obstacles) exist in state space. As the in nite number of states requires the use of function approximators such as backpropagation nets 16, 12, 24], we argue that these discontinuities imply severe di culties indoi:10.1007/bfb0019005 dblp:conf/ki/Linden92 fatcat:uwu6phlc7nbzdl4h67mmkwet4i