This is achieved probabilistically through interventions taken by the agent and then storing the results in a causal graph. It is a combination of both intrinsic curiosity in the reinforcement learning sense, that is exploration for its own sake, and the systematic recognition of causal connections through trial and error learning. Causally connected relationships in the agent’s environment are discovered through reinforcement learning and then expressed in terms of DAGs or causal equations that are understandable to humans.
In this sense causal curiosity has the potential to enable explainable AI, where we can lift the hood on the results of deep learning and view the causal connections that the agent is forming. Causal symbolic AI is therefore critical to enabling both the kind of general artificial intelligence that can operate in real world environments and one that is capable of communicating those decisions to humans.
Have questions, reach out at contact below.
Or check out our other offerings: