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...

A Human Factors Approach to Validating Driver Models for Interaction-aware Automated Vehicles

A major challenge for autonomous vehicles is interacting with other traffic participants safely and smoothly. A promising approach to handle such traffic interactions is equipping autonomous vehicles with interaction-aware controllers (IACs). These controllers predict how surrounding human drivers will respond to the autonomous vehicle’s actions...

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...

Training for Implicit Norms in Deep Reinforcement Learning Agents through Adversarial Multi-Objective Reward Optimization

We propose a deep reinforcement learning algorithm that employs an adversarial training strategy for adhering to implicit human norms alongside optimizing for a narrow goal objective. Previous methods which incorporate human values into reinforcement learning algorithms either scale poorly or assume hand-crafted state features. Our algorithm...

General-Sum Multi-Agent Continuous Inverse Optimal Control

Modeling possible future outcomes of robot-human interactions is of importance in the intelligent vehicle and mobile robotics domains. Knowing the reward function that explains the observed behavior of a human agent is advantageous for modeling the behavior with Markov Decision Processes (MDPs). However, learning the rewards that determine...

Social behavior for autonomous vehicles

Deployment of autonomous vehicles on public roads promises increased efficiency and safety. It requires understanding the intent of human drivers and adapting to their driving styles. Autonomous vehicles must also behave in safe and predictable ways without requiring explicit communication. We integrate tools from social psychology into...

Preference-driven demonstrations ranking for inverse reinforcement learning

New flexible teaching methods for robotics are needed to automate repetitive tasks that are currently still done by humans. For limited batch sizes, it is too expensive to teach a robot a new task (Smith & Anderson, 2014). Ideally, such flexible robots can be taught a new task by a non-expert. A non-expert is a person who knows the task the...