Bounded Rational Decision-Making in Changing Environments
This work addresses inefficiencies in decision-making for agents operating in dynamic environments, representing an incremental advance by extending bounded rationality frameworks to non-static conditions.
The paper tackles the problem of bounded rational decision-making in changing environments, where existing frameworks assume a static environment during computation, leading to utility inefficiencies when the environment changes. It quantifies these inefficiencies using concepts from non-equilibrium thermodynamics and illustrates their relationship with computational resources through simulations.
A perfectly rational decision-maker chooses the best action with the highest utility gain from a set of possible actions. The optimality principles that describe such decision processes do not take into account the computational costs of finding the optimal action. Bounded rational decision-making addresses this problem by specifically trading off information-processing costs and expected utility. Interestingly, a similar trade-off between energy and entropy arises when describing changes in thermodynamic systems. This similarity has been recently used to describe bounded rational agents. Crucially, this framework assumes that the environment does not change while the decision-maker is computing the optimal policy. When this requirement is not fulfilled, the decision-maker will suffer inefficiencies in utility, that arise because the current policy is optimal for an environment in the past. Here we borrow concepts from non-equilibrium thermodynamics to quantify these inefficiencies and illustrate with simulations its relationship with computational resources.