Name
Abstract | ||
|---|---|---|
During decision making and acting in the environment humans appraise decisions and observations with feelings and emotions. In this paper we propose a framework to incorporate an emotional model into the decision making process of a machine learning agent. We use a hierarchical structure to combine reinforcement learning with a dimensional emotional model. The dimensional model calculates two dimensions representing the actual affective state of the autonomous agent. For the evaluation of this combination, we use a reinforcement learning experiment (called Dyna Maze) in which, the agent has to find an optimal path through a maze. Our first results show that the agent is able to appraise the situation in terms of emotions and react according to them. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ROMAN.2014.6926309 | Edinburgh |
Keywords | Field | DocType |
control engineering computing,decision making,human-robot interaction,learning (artificial intelligence),mobile robots,path planning,affective states,decision making,dimensional emotional model,hierarchical structure,machine learning agent,optimal path,path-finding,reinforcement learning | Robot learning,Autonomous agent,Active learning (machine learning),Simulation,Computer science,Hyper-heuristic,Dimensional modeling,Artificial intelligence,Decision-making,Reinforcement learning,Learning classifier system | Conference |
ISSN | Citations | PageRank |
1944-9445 | 2 | 0.41 |
References | Authors | |
5 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Johannes Feldmaier | 1 | 2 | 0.41 |
| Klaus Diepold | 2 | 437 | 56.47 |