Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery
This addresses the problem of identifying causal structures for fields like decision-making and biology, representing an incremental advancement in combinatorial methods.
The authors tackled causal discovery by proposing CD-UCT, a model-based reinforcement learning method using tree search to incrementally build directed acyclic graphs, and it substantially outperformed state-of-the-art model-free reinforcement learning and greedy search in evaluations on synthetic and real-world datasets.
Identifying causal structure is central to many fields ranging from strategic decision-making to biology and economics. In this work, we propose CD-UCT, a model-based reinforcement learning method for causal discovery based on tree search that builds directed acyclic graphs incrementally. We also formalize and prove the correctness of an efficient algorithm for excluding edges that would introduce cycles, which enables deeper discrete search and sampling in DAG space. The proposed method can be applied broadly to causal Bayesian networks with both discrete and continuous random variables. We conduct a comprehensive evaluation on synthetic and real-world datasets, showing that CD-UCT substantially outperforms the state-of-the-art model-free reinforcement learning technique and greedy search, constituting a promising advancement for combinatorial methods.