An interface for defining policies that refer to a
This policy takes as input a policy for a belief MDP generated with
This class implements a Boltzmann policy where the the Q-values represent the components of the Boltzmann distribution.
This class can be used to lazily cache the policy of a source policy.
If you have a policy defined for one domain, and want to map it to use actions in another domain that have the same name, you can use this policy to perform the mapping.
This class defines a an epsilon-greedy policy over Q-values and requires a QComputable valueFunction to be specified.
A greedy policy that breaks ties by choosing the first action with the maximum value.
A greedy policy that breaks ties by randomly choosing an action amongst the tied actions.
This abstract class is used to store a policy for a domain that can be queried and perform common operations with the policy.
Class for storing an action and probability tuple.
A class for annotating an action selection, specified with a
A uniform random policy for single agent domains.
RuntimeException to be thrown when a Policy is queried for a state in which the policy is undefined.