Search

Supplementary Material 1

One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. The proposed algorithm finds an option which provably diminishes the expected number of steps to visit every state in the state space by a uniform random walk. We show empirically that the proposed algorithm improves the learning time in several domains with sparse rewards.

Objectives: This study was conducted to investigate the relationships among gender egalitarianism, sexual attitudes and sexual harassment myths among university students. Methods: A questionnaire survey was used with 165 male and 210 female university students. Descriptive statistics, independent t-test, one-way ANOVA, and the Pearson correlation coefficient with PASW 17.0 were used to analyze the data. Results: There were gender differences pertaining to gender egalitarianism and sexual harassment myths. Male students showed lower score in gender egalitarianism, were liberal on the topic of sexual pleasure and their outlook on free marriage and sexual permissiveness, and were more likely to agree on sexual harassment myths in excessive response, misunderstanding of behavior, responsibility of the victim, and an underestimation of the victim than female students. Conclusions: The results of this study indicate the existence of a gender gap regarding perceptions of egalitarianism, sexual attitudes and sexual harassment of between male and female university students. These findings suggest that the effort is needed to develop a program which allows university students to formulate sound sexual attitudes and values.