This paper aims at sharing some reflections and results concerning experiences carried out within a European interdisciplinary Erasmus+ project. The main themes are community peer mediation, considered from the perspective of educational innovation experimentation. Two on-line videorecorded meetings project analysed to show that process this article-writing was consistent with emerges as topic ...

The idea for this special issue was shaped via numerous conversations, where we shared our passion for, and belief in, action learning. As ‘comrades in adversity’ questioned each other on the va...

Good representations can help RL agents perform concise modeling of their surroundings, and thus support effective decision-making in complex environments. Previous methods learn good by imposing extra constraints on dynamics. However, the causal perspective, causation between action its effect is not fully considered those methods, which leads to ignorance underlying relations among effects tr...

Recently reinforcement learning has received much attention as a learning method (Sutton, 1988; Watkins & Dayan, 1992). It does not need a priori knowledge and has higher capability of reactive and adaptive behaviors. However, there are some significant problems in applying it to real problems. Some of them are deep cost of learning and large size of actionstate space. The Q-learning (Watkins &...

this article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for reinforcement learning agents. these definitions are used as a tool of knowledge transfer among agents. the agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. in other words, the agents are assumed t...