Characterising Interventions in Causal Games
This work addresses the challenge of designing safe AI systems through causal mechanism design and commitment, representing an incremental advancement in causal games.
The paper tackles the problem of answering causal queries in multi-agent settings by relaxing chronological constraints on interventions, resulting in a sound and complete set of primitive causal interventions that enable the study of arbitrarily complex interventional queries.
Causal games are probabilistic graphical models that enable causal queries to be answered in multi-agent settings. They extend causal Bayesian networks by specifying decision and utility variables to represent the agents' degrees of freedom and objectives. In multi-agent settings, whether each agent decides on their policy before or after knowing the causal intervention is important as this affects whether they can respond to the intervention by adapting their policy. Consequently, previous work in causal games imposed chronological constraints on permissible interventions. We relax this by outlining a sound and complete set of primitive causal interventions so the effect of any arbitrarily complex interventional query can be studied in multi-agent settings. We also demonstrate applications to the design of safe AI systems by considering causal mechanism design and commitment.