Analogy making as amortised model construction
This addresses the challenge of flexible and tractable model construction for AI agents, though it appears incremental as it builds on existing frameworks like Markov decision processes.
The paper tackles the problem of how agents can efficiently construct internal models for planning in novel situations by proposing that analogy enables reuse of solution-relevant structure from past experiences, amortizing computational costs of model construction and planning.
Humans flexibly construct internal models to navigate novel situations. To be useful, these internal models must be sufficiently faithful to the environment that resource-limited planning leads to adequate outcomes; equally, they must be tractable to construct in the first place. We argue that analogy plays a central role in these processes, enabling agents to reuse solution-relevant structure from past experiences and amortise the computational costs of both model construction (construal) and planning. Formalising analogies as partial homomorphisms between Markov decision processes, we sketch a framework in which abstract modules, derived from previous construals, serve as composable building blocks for new ones. This modular reuse allows for flexible adaptation of policies and representations across domains with shared structural essence.