A Language for Planning with Statistics
This addresses a specific issue in probabilistic planning for AI systems, but it appears incremental as it builds on existing statistical methods.
The paper tackles the sample size problem in planning by introducing an event-based language where probabilities are derived from observed event ratios, requiring introspection about their validity. It uses statistics and interval estimation to avoid decisions weakly supported by evidence.
When a planner must decide whether it has enough evidence to make a decision based on probability, it faces the sample size problem. Current planners using probabilities need not deal with this problem because they do not generate their probabilities from observations. This paper presents an event based language in which the planner's probabilities are calculated from the binomial random variable generated by the observed ratio of one type of event to another. Such probabilities are subject to error, so the planner must introspect about their validity. Inferences about the probability of these events can be made using statistics. Inferences about the validity of the approximations can be made using interval estimation. Interval estimation allows the planner to avoid making choices that are only weakly supported by the planner's evidence.