Learning to Initiate and Reason in Event-Driven Cascading Processes

We describe “Cascade”, a new counterfactual reasoning setup. An agent is provided a semantic instruction and the results of a played out dynamical system. Its goal is to intervene in the dynamic environment, triggering a cascade of events that will lead to a different and counterfactual outcome.

We devise an algorithm that learns to efficiently search in exponentially large semantic trees of possible event-driven futures. When provided with an observed cascade of events, it can also reason about alternative outcomes.

Abstract

Training agents to control a dynamic environment is a fundamental task in AI. In many environments, the dynamics can be summarized by a small set of events that capture the semantic behavior of the system. Typically, these events form chains or cascades. We often wish to change the system behavior using a single intervention that propagates through the cascade. For instance, one may trigger a biochemical cascade to switch the state of a cell or, in logistics, reroute a truck to meet an unexpected, urgent delivery. We introduce a new supervised learning setup called Cascade. An agent observes a system with known dynamics evolving from some initial state. The agent is given a structured semantic instruction and needs to make an intervention that triggers a cascade of events, such that the system reaches an alternative (counterfactual) behavior. We provide a test-bed for this problem, consisting of physical objects. We combine semantic tree search with an event-driven forward model and devise an algorithm that learns to efficiently search in exponentially large semantic trees. We demonstrate that our approach learns to follow instructions to intervene in new complex scenes. When provided with an observed cascade of events, it can also reason about alternative outcomes.

Cite the paper

@InProceedings{pmlr-v202-atzmon23a,
  title = 	 {Learning to Initiate and Reason in Event-Driven Cascading Processes},
  author =       {Atzmon, Yuval and Meirom, Eli and Mannor, Shie and Chechik, Gal},
  booktitle = 	 {Proceedings of the 40th International Conference on Machine Learning},
  pages = 	 {1218--1243},
  year = 	 {2023},
  editor = 	 {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan},
  volume = 	 {202},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {23--29 Jul},
  publisher =    {PMLR},
}