Expected utility
Expected utility is the probability-weighted average of the utility values of possible outcomes associated with an action or decision.
Grokking Bayes
Expected utility is the probability-weighted average utility of an action across possible outcomes.
- How it is used
- Guides choices under uncertainty by combining outcome probabilities with the value of their consequences.
- How deep it goes
- Defines and calculates discrete expected utility, extends it to continuous outcomes and sampling, then applies it to sequential decisions.
- Examples
- Uses website-launch payoffs, sampled conversion rates, and competing policies to show how probabilities, costs, and later choices affect decisions.
- What you can do after
- Apply it via probability-weighted sums or NumPy sampling to compare actions, and evaluate sequential choices by working backward through outcomes.
Timeless Algorithms, The Foundational Ideas
Expected utility is the probability-weighted average desirability of the possible outcomes of an action.
- How it is used
- Uses expected utility to turn posterior beliefs and preferences into choices under uncertainty.
- How deep it goes
- Develops the probability-weighted formulation, defines its terms, and compares actions using worked numerical calculations.
- Examples
- Works through a treatment decision after a positive test and a product launch versus delay under uncertain demand.
- What you can do after
- Evaluate actions under uncertainty by comparing expected utilities without mistaking a preferred decision for a guaranteed favorable outcome.
Read how Timeless Algorithms, The Foundational Ideas explains expected utility →
Causal AI
Expected utility is the probability-weighted average utility of possible outcomes under a specified action, policy, or intervention.
- How it is used
- Select actions, policies, or treatment regimes by comparing their probability-weighted utilities under specified interventions.
- How deep it goes
- Defines maximization and contrasts observational with interventional expectations, then demonstrates implementation and parameter sensitivity.
- Examples
- Uses debt-versus-equity investment decisions, a causal Bayesian network, changed outcome probabilities, and Newcomb’s paradox.
- What you can do after
- Apply expected utility through Python inference workflows to compare observational and interventional decisions.
Also covered in
What to know first
- Bayesian inferenceBayesian inference updates probability distributions over hypotheses or unknown quantities by combining prior information with observed evidence and a likelihood model.
- actionAn action is a choice or operation selected or performed by an actor that can affect a system, environment, or process.
- probabilityProbability is a mathematical measure, from zero to one, of the likelihood that an event or outcome occurs or is true.
- objective functionAn objective function is a mathematical function that assigns values to candidate solutions or parameter settings, which an optimization procedure seeks to minimize or maximize.
Related concepts
- probabilityuses · Probability is a mathematical measure, from zero to one, of the likelihood that an event or outcome occurs or is true.
- utility functionuses · A utility function maps outcomes or alternatives to numerical values representing their desirability or preference for a decision maker or objective.
- decision treeused by · A decision tree is a tree-structured model or representation in which successive tests or choices lead through branches to outcomes, predictions, or actions.
- information gainequivalent to · Information gain is the decrease in uncertainty resulting from information or an observation, often quantified as a reduction in entropy.
Questions about expected utility
What is expected utility?
Expected utility is the probability-weighted average of the utility values of possible outcomes associated with an action or decision.
Which Manning books explain expected utility?
Grokking Bayes, Timeless Algorithms, The Foundational Ideas and Causal AI.
What should I know before learning expected utility?
Manning books that teach expected utility usually introduce Bayesian inference, action, probability and objective function first.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


