Soar-RL: integrating reinforcement learning with Soar

Authors:
Shelley Nason;John E. Laird
Affiliations:
University of Michigan, 1101 Beal Avenue, Ann Arbor, MI 48109-2110, USA;University of Michigan, 1101 Beal Avenue, Ann Arbor, MI 48109-2110, USA
Venue:
Cognitive Systems Research
Year:
2005

Citing 2
Cited 9

Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning

Artificial Intelligence
Hierarchical reinforcement learning with the MAXQ value function decomposition

Journal of Artificial Intelligence Research

Affect, Anticipation, and Adaptation: Affect-Controlled Selection of Anticipatory Simulation in Artificial Adaptive Agents

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Cognitive Principles for Information Management: The Principles of Mnemonic Associative Knowledge (P-MAK)

Minds and Machines
Strategies for Affect-Controlled Action-Selection in Soar-RL

IWINAC '07 Proceedings of the 2nd international work-conference on Nature Inspired Problem-Solving Methods in Knowledge Engineering: Interplay Between Natural and Artificial Computation, Part II
Extending the Soar Cognitive Architecture

Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Analogical learning in a turn-based strategy game

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Reinforcement learning as heuristic for action-rule preferences

ProMAS'10 Proceedings of the 8th international conference on Programming Multi-Agent Systems
Exploiting persistent mappings in cross-domain analogical learning of physical domains

Artificial Intelligence
Game designers training first person shooter bots

AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence
Deconstructing reinforcement learning in sigma

AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe an architectural modification to Soar that gives a Soar agent the opportunity to learn statistical information about the past success of its actions and utilize this information when selecting an operator. This mechanism serves the same purpose as production utilities in ACT-R, but the implementation is more directly tied to the standard definition of the reinforcement learning (RL) problem. The paper explains our implementation, gives a rationale for adding an RL capability to Soar, and shows results for Soar-RL agents' performance on two tasks.