Chronological Causal Bandits
This addresses decision-making in dynamic causal environments for applications like sequential interventions, but it is incremental as it builds on existing causal bandit frameworks.
The paper tackles the problem of multiple causal multi-armed bandits operating sequentially in a dynamic system, where rewards depend on a causal model that changes over time and allows information transfer between agents. It introduces the Chronological Causal Bandit (CCB) and demonstrates early findings on a toy problem.
This paper studies an instance of the multi-armed bandit (MAB) problem, specifically where several causal MABs operate chronologically in the same dynamical system. Practically the reward distribution of each bandit is governed by the same non-trivial dependence structure, which is a dynamic causal model. Dynamic because we allow for each causal MAB to depend on the preceding MAB and in doing so are able to transfer information between agents. Our contribution, the Chronological Causal Bandit (CCB), is useful in discrete decision-making settings where the causal effects are changing across time and can be informed by earlier interventions in the same system. In this paper, we present some early findings of the CCB as demonstrated on a toy problem.