Soar capabilities
- Reinforcement learning
- None.
- None.
- None.
- John Laird
In this category, you'll find a variety of agents developed for a wide range of different tasks and environments. You will find a full description of the agent, its capabilities and problem solving approach as well, as a download link. If the agent requires an environment, a link will be provided. We'd highly encourage you to submit your own agents for use by the greater Soar community. To do so, you can send your zipped up submission with a full description (try to include all of the type of information we include on each download page) to mazina@umich.edu with the subject "Soar Agent Submission".
-
Reinforcement Learning Unit Test
-
Created by:
Soar
Reinforcement Learning Unit Test
An agent that tests four rl-rule sequence cases to behaviorally test the Soar reinforcement learning update mechanism. Learning/discount-rate are set to known values and other parameters can be tweaked. Some of the expected behavior is documented in the README file included.
Soar capabilities -
Created by:
-
Soar 7 Agents
-
Created by:
Soar 7 Agents
This is a collection of all the demo agents that were distributed with Soar 7.
It includes:- Blocks World
- Eight puzzle
- Farmer
- Kab
- Missionaries and Cannibals
- Safe Stack
- Tower of Hanoi
- Waterjug
- Various
- None.
- None.
- None.
- John Laird
- Soar 7
- Plain text
-
Created by:
-
Blocks-World (Subgoaling)
-
Created by:
Blocks-World (Subgoaling)
This agent is a modified version of the simple blocks-world agent that uses means-ends analysis and operator subgoaling (first used in General Problem Solver (GPS)).
Means-ends analysis involves proposing operators that can achieve part of the goal. Thus, some operators will be proposed even if they do not apply to the current state. If an operator is selected that can not apply, an operator no-change impasse arises. In that substate, the goal is to achieve a state in which the impassed... -
Created by:
-
Arithmetic (with Semantic Memory)
-
Created by:
Arithmetic (with Semantic Memory)
This agent demonstrates the use of semantic memory by extending the capabilities of the Arithmetic Agent. The description of that agent also applies here.
This agent supports using semantic memory through in three different ways controlled by parameters set in initialize-arithmetic.- If the semantic or working memory is pre-loaded with problems, it will use those problems. If not it will generate problems at random.
- problems-5000.soar and problems-10000.soar contain the rules to
-
Created by:
-
Eaters (Semantic Error Example)
-
Created by:
Eaters (Semantic Error Example)
A very simple move to food agent that contains a few semantic errors for people new to Soar to debug and correct.
Soar capabilities- N/A
- This agent is packaged with the Eaters environment.
- None.
- John Laird
- Soar 8,9
- Plain text
-
Created by:
-
Eaters (Syntax Error Example)
-
Created by:
Eaters (Syntax Error Example)
A very simple move to food agent that contains a few syntax errors for people new to Soar to correct.
Soar capabilities- N/A
- This agent is packaged with the Eaters environment.
- None.
- John Laird
- Soar 8,9
- Plain text
-
Created by:
-
Eaters (Move North 2)
-
Created by:
Eaters (Move North 2)
A very simple eaters agent that repeatedly moves the eater north.
Soar capabilities- Basic PSCM functions: Operator Proposal, Operator Evaluation, Internal Operator Application
- Using the output-link to perform an action in the environment
- This agent is packaged with the Eaters environment.
- None.
- John Laird
- Soar 8,9
- Simple text
-
Created by:
-
Eaters (Move To Food)
-
Created by:
Eaters (Move To Food)
A very simple eaters agent that proposes the move-to-food operator in any direction that contains normal or bonus food. If there is no food nearby, no instances of the operator will be proposed and the halt operator will be proposed.
Soar capabilities- Basic PSCM functions: Operator Proposal, Operator Evaluation, Internal Operator Application
- Demonstrates using percepts from the input link to propose a context-sensitive operator
- This agent is packaged with the Eaters
-
Created by:
-
Eaters (Move)
-
Created by:
Eaters (Move)
An eaters agent that implements a generalized move operator that proposes moves to any adjacent position that is empty, has food or contains another eater. It prefers operators that move towards bonus food and avoids operators that move to empy spots or ones with an eater in them.
Soar capabilities- Basic PSCM functions: State Elaboration, Operator Proposal, Operator Evaluation, Internal Operator Application
- This agent is packaged with the Eaters environment.
-
Created by:
-
Eaters (Move North)
-
Created by:
Eaters (Move North)
A very simple eaters agent that moves the eater north once.
Soar capabilities- Basic PSCM functions: Operator Proposal, Internal Operator Application
- Using the output-link to perform an action in the environment
- This agent is packaged with the Eaters environment.
- None.
- John Laird
- Soar 8,9
- Simple text
-
Created by:
There are no articles in this category.