5 papers
Using Feasible Action-Space Reduction by Groups to fill Causal Responsibility Gaps in Spatial Interactions
Ashwin George, Vassil Guenov, Arkady Zgonnikov +2
Heralding the advent of autonomous vehicles and mobile robots that interact with humans, responsibility in spatial interaction is burgeoning as a research topic. Even though metric…
Feasible Action Space Reduction for Quantifying Causal Responsibility in Continuous Spatial Interactions
Ashwin George, Luciano Cavalcante Siebert, David A. Abbink +1
Understanding the causal influence of one agent on another agent is crucial for safely deploying artificially intelligent systems such as automated vehicles and mobile robots into…
Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
Ashwin George, Lucas Elbert Suryana, Lorenzo Flipse +5
Partial driving automation creates a tension: drivers remain legally responsible for vehicle behaviour, yet their active control is significantly reduced. This reduction undermines…
CoMI-IRL: Contrastive Multi-Intention Inverse Reinforcement Learning
Antonio Mone, Frans A. Oliehoek, Luciano Cavalcante Siebert
Inverse Reinforcement Learning (IRL) seeks to infer reward functions from expert demonstrations. When demonstrations originate from multiple experts with different intentions, the…
Explaining Learned Reward Functions with Counterfactual Trajectories
Jan Wehner, Frans Oliehoek, Luciano Cavalcante Siebert
Learning rewards from human behaviour or feedback is a promising approach to aligning AI systems with human values but fails to consistently extract correct reward functions. Inter…