| Interface | Description |
|---|---|
| ValueFunctionInitialization |
This interface may be used by planning and learning algorithms that require an initialization value for the Q-value function or the value function.
|
| Class | Description |
|---|---|
| EpisodeAnalysis |
This class is used to keep track of all events that occur in an episode.
|
| EpisodeSequenceVisualizer |
This class is used to visualize a set of episodes that have been saved to files in a common directory or which are
provided to the object as a list of
EpisodeAnalysis objects. |
| Policy |
This abstract class is used to store a policy for a domain that can be queried and perform common operations with the policy.
|
| Policy.ActionProb |
Class for storing an action and probability tuple.
|
| Policy.RandomPolicy |
A uniform random policy for single agent domains.
|
| QValue |
This class is used to store Q-values.
|
| ValueFunctionInitialization.ConstantValueFunctionInitialization |
A
ValueFunctionInitialization implementation that always returns a constant value. |
| Exception | Description |
|---|---|
| Policy.PolicyUndefinedException |
RuntimeException to be thrown when a Policy is queried for a state in which the policy is undefined.
|