Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learning
On Pareto optimality in social distance games
Preference-based inconsistency-tolerant query answering under existential rules
Inhomogeneous deep Q-network for time sensitive applications
Predicting voting outcomes in the presence of communities, echo chambers and multiple parties
Q-Learning-based model predictive variable impedance control for physical human-robot collaboration
PredDiff: Explanations and interactions from conditional expectations
Simplified Risk-aware Decision Making with Belief-dependent Rewards in Partially Observable Domains
Atlas of AI – Book review