| dc.description.abstract | This thesis explores the field of machine ethics and safety-critical intelligent machines. Machine ethics is concerned with ensuring that artificial autonomous systems possess moral guidelines, so that these systems are acting ethically and prevent harm. To ensure that an autonomous system is acting ethically, a method is explored by implementing and investigating a specific approach for training reinforcement learning agents, where the learned policy is both explainable and interpretable. The approach achieves this by utilizing a logical reasoning engine to learn the environment. Such a system should, in theory, have the capability of reasoning, continuous learning, and most importantly, transparency, all of which are argued to be critical properties of autonomous ethical agents. The system is trained and verified in a synthetic symbolic environment, where the states of the environment are a set of boolean perceptions. The agent in the environment acts as an assistant robot, where the objective of the agent is to learn and infer the correct rules for each of its possible actions. The idea of the method is that this allows the autonomous system to learn a verifiable ethical guideline embedded in the environment. The experiments are run on environments with increasing complexity, in both the number of actions the agent can perform as well as the number of perceptions the agent sense from the environment. The produced results show that the proposed system is capable of inferring relatively elementary logical action rules that correspond to the state of the environment. For more complex environments, the learned actions do not allow for much generality, and the method does not scale well in terms of the needed provided background knowledge. | eng |