com.cra.figaro.algorithm.decision
AnytimeDecisionMetropolisHastings
A message instructing the handler to compute the distribution of the target element.
A message instructing the handler to compute the distribution of the target element.
A message instructing the handler to compute the expectation of the target element under the given function.
A message instructing the handler to compute the expectation of the target element under the given function.
A message instructing the handler to compute the probability of the predicate for the target element.
A message instructing the handler to compute the probability of the predicate for the target element.
A message from the handler containing the distribution of the previously requested element.
A message from the handler containing the distribution of the previously requested element.
A message from the handler containing the expected value of the previously requested element and function.
A message from the handler containing the expected value of the previously requested element and function.
A message from the handler containing the probability of the previously requested predicate and element.
A message from the handler containing the probability of the previously requested predicate and element.
A class representing the actor running the algorithm.
A class representing the actor running the algorithm.
A sample is a map from elements to their values.
A sample is a map from elements to their values.
Get the acceptance ratio for the sampler.
Get the acceptance ratio for the sampler.
Number of samples that should be taken in a single step of the algorithm.
Number of samples that should be taken in a single step of the algorithm.
Clean up the sampler, freeing memory.
Clean up the sampler, freeing memory.
Cleans up the temporary elements created during sampling
Cleans up the temporary elements created during sampling
Return an estimate of the marginal probability distribution over the target that lists each element with its probability.
Return an estimate of the marginal probability distribution over the target that lists each element with its probability.
Return an estimate of the expectation of the function under the marginal probability distribution of the target.
Return an estimate of the expectation of the function under the marginal probability distribution of the target.
Return an estimate of the probability of the predicate under the marginal probability distribution of the target.
Return an estimate of the probability of the predicate under the marginal probability distribution of the target.
Compute the utility of each parent/decision tuple and return a DecisionSample.
Compute the utility of each parent/decision tuple and return a DecisionSample. Each decision algorithm must define how this is done since it is used to set the policy for a decision. For sampling algorithms, this will me a map of parent/decision tuples to a utility and a weight for that combination. For factored algorithms, the DecisionSample will contain the exact expected utility with a weight of 1.0.
The actor running the algorithm.
The actor running the algorithm.
Set this flag to true to obtain debugging information.
Set this flag to true to obtain debugging information.
Return an estimate of the marginal probability distribution over the target that lists each element with its probability.
Return an estimate of the marginal probability distribution over the target that lists each element with its probability. The result is a lazy stream. It is up to the algorithm how the stream is ordered. Throws NotATargetException if called on a target that is not in the list of targets of the algorithm. Throws AlgorithmInactiveException if the algorithm is inactive.
Return an estimate of the expectation of the function under the marginal probability distribution of the target.
Return an estimate of the expectation of the function under the marginal probability distribution of the target. Throws NotATargetException if called on a target that is not in the list of targets of the algorithm. Throws AlgorithmInactiveException if the algorithm is inactive.
Number of samples taken.
Number of samples taken.
Get the total utility and weight for a specific value of a parent and decision.
Get the total utility and weight for a specific value of a parent and decision.
Get the total utility and weight for all sampled values of the parent and decision.
Get the total utility and weight for all sampled values of the parent and decision.
A handler of services provided by the algorithm.
A handler of services provided by the algorithm.
Initialize the sampler.
Initialize the sampler.
Kill the algorithm so that it is inactive.
Kill the algorithm so that it is inactive. It will no longer be able to provide answers.Throws AlgorithmInactiveException if the algorithm is not active.
Return the mean of the probability density function for the given continuous element.
Return the mean of the probability density function for the given continuous element.
Return an element representing the posterior probability distribution of the given element.
Return an element representing the posterior probability distribution of the given element.
Return an estimate of the probability that the target produces the value.
Return an estimate of the probability that the target produces the value. Throws NotATargetException if called on a target that is not in the list of targets of the algorithm. Throws AlgorithmInactiveException if the algorithm is inactive.
Return an estimate of the probability of the predicate under the marginal probability distribution of the target.
Return an estimate of the probability of the predicate under the marginal probability distribution of the target. Throws NotATargetException if called on a target that is not in the list of targets of the algorithm. Throws AlgorithmInactiveException if the algorithm is inactive.
Resume the computation of the algorithm, if it has been stopped.
Resume the computation of the algorithm, if it has been stopped. Throws AlgorithmInactiveException if the algorithm is not active.
Run a single step of the algorithm.
Run a single step of the algorithm. The algorithm must be able to provide answers after each step.
Produce a single sample.
Produce a single sample. In decision MH, we always update the target (parent and decision) since the utilities mights have changed
Sets the policy for the given decision.
Sets the policy for the given decision. This will get the computed utility of the algorithm and call setPolicy on the decision. Note there is no error checking here, so the decision in the argument must match the target decision in the algorithm.
Release all resources from this anytime algorithm.
Release all resources from this anytime algorithm.
Start the algorithm and make it active.
Start the algorithm and make it active. After it returns, the algorithm must be ready to provide answers. Throws AlgorithmActiveException if the algorithm is already active.
Stop the algorithm from computing.
Stop the algorithm from computing. The algorithm is still ready to provide answers after it returns. Throws AlgorithmInactiveException if the algorithm is not active.
Override the stopUpdate function in anytime to call the sampler update function
Override the stopUpdate function in anytime to call the sampler update function
Test Metropolis-Hastings by repeatedly running a single step from the same initial state.
Test Metropolis-Hastings by repeatedly running a single step from the same initial state. For each of a set of predicates, the fraction of times the predicate is satisfied by the resulting state is returned. By the resulting state, we mean the new state if it is accepted and the original state if not.
Return the variance of the probability density function for the given continuous element.
Return the variance of the probability density function for the given continuous element.
Anytime Decision Metropolis-Hastings sampler.