Neural Networks and Statistical Learning by Ke-Lin Du & M. N. S. Swamy

Author:Ke-Lin Du & M. N. S. Swamy
Language: eng
Format: epub
ISBN: 9781447174523
Publisher: Springer London

17.5 Learning from Demonstrations

As a wrong action can result in unrecoverable effects, this poses a safety–exploration dilemma, especially for a model-free approach. A common approach to safety consists of assigning negative rewards for undesired transitions, such that the most reliable policy maximizes the minimal sum of reward in the presence of uncertainties and stochasticity, yielding a worst-case or minimax problem. By assigning a negative reward, the variance of the return can be taken into account by adopting risk-sensitivity approaches [31]. There are three approaches to safe exploration [12]:providing initial knowledge, directing the learning in its initial stage toward more profitable and safer regions of the state space;

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.