What would it take to build an agent whose behaviour is derived from a few fundamentals the way physics is derived from conservation laws? Three types, four axioms, and a refusal to add anything else.
Most agents are given a fixed set of decision rules. Credence's second tier generates candidate rules from sensor features, scores them by complexity, and lets the posterior decide which structures are worth keeping. This is program synthesis as Bayesian inference.
Every RL agent that has played a text adventure has tried to take the lantern fifty times in a row. The fix is not better exploration heuristics. The fix is representing state properly.