Abstract
Transport theory describes the scattering behavior of physical particles such as photons. Here we show how to connect this theory to optimal control theory and to adaptive behavior of agents embedded in an environment. Environments and tasks are defined by physical boundary conditions. Given some task, we compute a set of probability densities on continuous state and action and time. From these densities we derive an optimal policy such that for all states the most likely action maximizes the probability of reaching a predefined goal state. Liouville’s conservation theorem tells us that the conditional density al time t, state s, and action a must equal the density at t+ dt, s+ ds, a+ da. Discretization yields a linear system that can be solved directly and whose solution corresponds to an optimal policy. Discounted reward schemes are incorporated naturally by taking the Laplace transform of the equations. The Liouville machine quickly solves rather complex maze problems.
Original language | English (US) |
---|---|
Pages (from-to) | 105-118 |
Number of pages | 14 |
Journal | Adaptive Behavior |
Volume | 9 |
Issue number | 2 |
DOIs | |
State | Published - Jan 1 2001 |
Externally published | Yes |
ASJC Scopus subject areas
- Behavioral Neuroscience
- Experimental and Cognitive Psychology