• Corpus ID: 9656121

Extending soar with dissociated symbolic memories

@inproceedings{Derbinsky2010ExtendingSW,
  title={Extending soar with dissociated symbolic memories},
  author={Nate Derbinsky and John E. Laird},
  year={2010}
}
Over long lifetimes, learning agents accumulate large stores of knowledge. To support human-level decision-making, their cognitive architectures must efficiently manage this experience and bring to bear pertinent data to act in the world.Prior psychological and computational work suggests the need for multiple, dissociated memory systems, citing significant functional and computational tradeoffs that arise when implementing a single memory mechanism for different types of learning tasks. In… 

Figures from this paper

Long-Term Symbolic Memories for Long-Living Learning Agents
We humans, as prime exemplars of long-lived, learning agents, are frequently bombarded with dense and varying torrents of information, including data that is autobiographical (Laird & Derbinsky,
Exploring the Space of Computational Memory Models
TLDR
A direction of empirical, computational research is proposed that seeks to better understand the behavioural dynamics that arise when an agent endowed with long-term memory is situated in a task, by determining which properties of task and characteristics of memory systems in combination are responsible for which aspects of behaviour.
Performance evaluation of declarative memory systems in Soar
TLDR
This paper evaluates 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, indicating that the implementation is sufficient for tasks of this length.
Competence-preserving retention of learned knowledge in soar's working and procedural memories
TLDR
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.
A Case Study of Knowledge Integration Across Multiple Memories in Soar
Effective and Efficient Management of Soar's Working Memory via Base-Level Activation
TLDR
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.
Architectural Mechanisms for Mitigating Uncertainty during Long-Term Declarative Knowledge Access
Long-term declarative semantic memory is a key component of a cognitive architecture that allows an agent to perform effectively in complex tasks. Over the years, a number of new mechanisms beyond
A review of long-term memory in natural and synthetic systems
TLDR
A novel methodology is applied that incorporates neuroethological approaches with general biological inspiration in the design of synthetic cognitive systems and four fundamental functional principles are derived that are in accordance with neuroscientific theory: priming, cross-modal associations, cross/modal coordination without semantic information transfer, and global system behavior resulting from activation dynamics within the memory system.
An Architecture Approach to Modeling the Remote Associates Test
TLDR
This paper investigates how the choice of knowledge base and agent strategy impact difficulty on the RAT while providing a more comprehensive account for human difficulty on this task in terms of cognitive architecture components.
...
...

References

SHOWING 1-10 OF 36 REFERENCES
Large Declarative Memories in ACT-R
TLDR
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.
Efficiently Implementing Episodic Memory
TLDR
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.
Extending the Soar Cognitive Architecture
TLDR
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.
Comprehensive Working Memory Activation in Soar
TLDR
This paper presents a comprehensive implementation of working memory activation in Soar that takes advantage of the unique characteristic of Soar's working memory structure, namely persistence.
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
Enhancing intelligent agents with episodic memory
The Evolution of Multiple Memory Systems
TLDR
It is shown that functional incompatibility occurs for a number of the distinctions that have been proposed between memory systems and the conditions under which memory systems could evolve to serve a wide range of functions.
Learning to use episodic memory
An integrated theory of the mind.
TLDR
The perceptual-motor modules, the goal module, and the declarative memory module are presented as examples of specialized systems in ACT-R, which consists of multiple modules that are integrated to produce coherent cognition.
Modeling Integration and Dissociation in Brain and Cognitive Development
TLDR
A computational framework for understanding the specialization of brain functions across the hippocampus, neocortex, and basal ganglia is presented, based on computational tradeoffs that arise in neural network models.
...
...