
Reasoning in Bayesian Opinion Exchange Networks Is PSPACEHard
We study the Bayesian model of opinion exchange of fully rational agents...
read it

Pessimism About Unknown Unknowns Inspires Conservatism
If we could define the set of all bad outcomes, we could hardcode an ag...
read it

HeterogeneousAgent Trajectory Forecasting Incorporating Class Uncertainty
Reasoning about the future behavior of other agents is critical to safe ...
read it

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
Much of modelbased reinforcement learning involves learning a model of ...
read it

Efficient Bayesian Learning in Social Networks with Gaussian Estimators
We consider a group of Bayesian agents who try to estimate a state of th...
read it

Inferring Agents Preferences as Priors for Probabilistic Goal Recognition
Recent approaches to goal recognition have leveraged planning landmarks ...
read it

Formal methods for aN Iterated volunteer's dilemma
Game theory provides a paradigm through which we can study the evolving ...
read it
The Bounded Bayesian
The ideal Bayesian agent reasons from a global probability model, but real agents are restricted to simplified models which they know to be adequate only in restricted circumstances. Very little formal theory has been developed to help fallibly rational agents manage the process of constructing and revising small world models. The goal of this paper is to present a theoretical framework for analyzing model management approaches. For a probability forecasting problem, a search process over small world models is analyzed as an approximation to a largerworld model which the agent cannot explicitly enumerate or compute. Conditions are given under which the sequence of smallworld models converges to the largerworld probabilities.
READ FULL TEXT
Comments
There are no comments yet.