• Corpus ID: 11725225

Performance evaluation of declarative memory systems in Soar

  title={Performance evaluation of declarative memory systems in Soar},
  author={John E. Laird and Nate Derbinsky and Jonathan Voigt},
A rarely studied issue with using persistent computational models is whether the underlying computational mechanisms scale as knowledge is accumulated through learning. In this paper we evaluate the declarative memories of Soar: working memory, semantic memory, and episodic memory, using a detailed simulation of a mobile robot running for one hour of real-time. Our results indicate that our implementation is sufficient for tasks of this length. Moreover our system executes orders of magnitudes… 
Effective and Efficient Management of Soar's Working Memory via Base-Level Activation
This paper documents a functionality-driven exploration of automatic working-memory management in Soar and presents empirical results, which demonstrate both that the mechanism performs with little computational overhead and that it helps maintain the reactivity of a Soar agent contending with long-term, autonomous simulated robotic exploration as it reasons using large amounts of acquired information.
Algorithms for scaling in a general episodic memory
The evaluation of an algorithmic variant to the task-independent episodic memory of Soar that expands the class of tasks and cues the mechanism can support while remaining reactive over long agent lifetimes is presented.
A Multi-Domain Evaluation of Scaling in a General Episodic Memory
This paper reviews the implementation of episodic memory in Soar and presents an expansive evaluation of that system, demonstrating useful applications of episodi memory across a variety of domains, including games, mobile robotics, planning, and linguistics.
Competence-preserving retention of learned knowledge in soar's working and procedural memories
This paper evaluates one approach to forgetting knowledge that is not in active use and can likely be reconstructed if it becomes relevant, and applies this model for selective retention of learned knowledge to the working and procedural memories of Soar.
Extending Semantic and Episodic Memory to Support Robust Decision Making
  • J. Laird
  • Computer Science, Psychology
  • 2013
For episodic memory, research has led to significant improvements in the efficiency of storage and retrieval through the exploitation of temporal contiguity, structural regularity, high cue structural selectivity, high temporal selectivity and low cue feature co-occurrence.
Cognitive Robotics Using the Soar Cognitive Architecture
Research in mobile robotics, relational and continuous model learning, and learning by situated, interactive instruction is presented, which improves Soar abilities for control of robots.
Long-Term Declarative Memory for Generally Intelligent Agents
The goal of my research is to develop and evaluate long-term declarative memory mechanisms that are effective and efficient across a variety of tasks.
Situated comprehension of imperative sentences in embodied, cognitive agents
In this paper, embodied agents instantiated in Soar cognitive architecture are described that use context derived from their linguistic, perceptual, procedural and semantic knowledge for comprehending imperative sentences.
Endowing a Cognitive Architecture with World Knowledge
The Wikipedia knowledge base is used to derive a declarative database for the ACT-R cognitive architecture, complete both with tens of millions of world-knowledge facts and with estimates of the accessibility (activation) of these facts.


Large Declarative Memories in ACT-R
This paper motivates and describes the interfacing of theACT-R cognitive architecture with a relational database to support large declarative memories within ACT-R models.
Concurrent Knowledge Activation Calculation in Large Declarative Memories
The alternative exploits concurrency features of the Erlang programming language to extend the practicality of ACT-R’s retrieval mechanisms to new levels of scale and illustrates how concurrency can accelerate calculation in other architectures struggling to support large associative declarative memories.
Efficiently Implementing Episodic Memory
Whether even with intractable asymptotic growth, it is possible to develop efficient algorithms and data structures for episodic memory systems that are practical for real-world tasks is explored.
Towards efficiently supporting large symbolic declarative memories
This paper details data structures and algorithms for an efficient mechanism over a large set of retrievals, as well as for a class of activation bias, in the development of large-scale cognitive models.
Extending soar with dissociated symbolic memories
A memory-centric analysis of Soar 9 is developed, a general cognitive architecture that incorporates multiple long-term memories that explores the functional abilities, computational opportunities, and theoretical challenges entailed by integrating a diverse set of symbolic memory systems.
Extending Cognitive Architecture with Episodic Memory
The hypothesis that episodic memory is a critical component for cognitive architectures that support general intelligence is explored and an implementation is presented that supports a wealth of cognitive capabilities that are difficult to attain without it.
A Year of Episodic Memory
Endowing an intelligent agent with an episodic memory provides knowledge that is invaluable for acting in the present, as well as supporting a wide range of cognitive capabilities. However, affording
Extending the Soar Cognitive Architecture
This paper presents the cognitive architecture approach to general intelligence and the traditional, symbolic Soar architecture, followed by major additions to Soar: non-symbolic representations, new learning mechanisms, and long-term memories.
A Generic Memory Module for Events
A set of general requirements that any memory module should provide regarding memory encoding, storage and retrieval is proposed and an implementation that satisfies these requirements is presented, which is evaluated on three different tasks: plan synthesis, plan recognition and Physics problem solving.
Integrating, Execution, Planning, and Learning in Soar for External Environments
How the Soar architecture supports planning, execution, and learning in unpredictable and dynamic environments is described and capabilities are demonstrated on two robotic systems controlled by Soar.