Context-specific value inference via hybrid intelligence

Human values are the abstract motivations that drive our opinions and actions. AI agents ought to align their behavior with our value preferences (the relative importance we ascribe to different values) to co-exist with us in our society. However, value preferences differ across individuals and are dependent on context. To reflect diversity in...

MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning

Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single reward model, thus rendering it difficult to trade off different reward functions from multiple experts. We...

Does Personalization Help? Predicting How Social Situations Affect Personal Values

Personal values represent what people find important in their lives, and are key drivers of human behavior. For this reason, support agents should provide help that is aligned with the personal values of the users. To do this, the support agent not only should know the value preferences of the user, but also how different situations in the...

Aligning AI with Human Norms: Multi-Objective Deep Reinforcement Learning with Active Preference Elicitation

The field of deep reinforcement learning has seen major successes recently, achieving superhuman performance in discrete games such as Go and the Atari domain, as well as astounding results in continuous robot locomotion tasks. However, the correct specification of human intentions in a reward function is highly challenging, which is why state...

Discrete state-space active inference and unknown controlled state transitions

Active inference is a process theory arising from neuroscience which casts perception, action, planning and learning under one optimisation criterion: minimisation of free energy. Current literature on the implementation of discrete state-space active inference focuses on scalability, the comparison to reinforcement learning and its performance...