HOUSE_OVERSIGHT_013048.jpg

132 7 A Formal Model of Intelligent Agents

7.2.2 Memory Stores

As well as goals, we introduce into the model a long-term memory and a workspace. Regarding
long-term memory we assume the agent's memory consists of multiple memory stores corre-
sponding to various types of memory, e.g.: procedural (K_Proc), declarative (K_Dec), episodic
(K_Ep), attentional (K_Att) and Intentional (K_Int). In Appendix ?? a category-theoretic model
of these memory stores is introduced; but for the moment, we need only assume the existence
of

• an injective mapping Θ_Ep : K_Ep → H where H is the space of fuzzy sets of subhistories
(subhistories being “episodes” in this formalism)
• an injective mapping Θ_Proc : K_Proc × M × W → A, where M is the set of memory states,
W is the set of (observation, goal, reward) triples, and A is the set of actions (this maps
each procedure object into a function that enacts actions in the environment or memory,
based on the memory state and current world-state)
• an injective mapping Θ_Dec : K_Dec → L, where L is the set of expressions in some formal lan-
guage (which may for example be a logical language), which possesses words corresponding
to the observations, goals, reward values and actions in our agent formalism
• an injective mapping Θ_Int : K_Int → G, where G is the space of goals mentioned above
• an injective mapping Θ_Att : K_Int ∪ K_Ep ∪ K_Proc ∪ K_Ec → V, where V is the space of
“attention values” (structures that gauge the importance of paying attention to an item of
knowledge over various time-scales or in various contexts)

We also assume that the vocabulary of actions contains memory-actions corresponding to the
operations of inserting the current observation, goal, reward or action into the episodic and/or
declarative memory store. And, we assume that the activity of the agent, at each time-step,
includes the enaction of one or more of the procedures in the procedural memory store. If several
procedures are enacted at once, then the end result is still formally modeled as a single action
a = a_[1] * ... * a_[k] where * is an operator on action-space that composes multiple actions into a
single one.

Finally, we assume that, at each time-step, the agent may carry out an external action a_i
on the environment, a memory action m_i on the (long-term) memory, and an action b_i on its
internal workspace. Among the actions that can be carried out on the workspace, are the
ability to insert or delete observations, goals, actions or reward-values from the workspace.
The workspace can be thought of as a sort of short-term memory or else in terms of Baars’
“global workspace” concept mentioned above. The workspace provides a medium for interaction
between the different memory types.

The workspace provides a mechanism by which declarative, episodic and procedural memory
may interact with each other. For this mechanism to work, we must assume that there are
actions corresponding to query operations that allow procedures to look into declarative and
episodic memory. The nature of these query operations will vary among different agents, but
we can assume that in general an agent has

• one or more procedures Q_Dec(x) serving as declarative queries, meaning that when Q_Dec is
enacted on some x that is an ordered set of items in the workspace, the result is that one
or more items from declarative memory is entered into the workspace
• one or more procedures Q_Ep(x) serving as episodic queries, meaning that when Q_Ep is
enacted on some x that is an ordered set of items in the workspace, the result is that one
or more items from episodic memory is entered into the workspace

HOUSE_OVERSIGHT_013048