Announcement

Collapse
No announcement yet.

Search Result

Collapse
5 results in 0.0024 seconds.

You can also choose from the popular tags.


  • Water Jug (Reinforcement Learning)

    Water Jug (Reinforcement Learning)

    This agent demonstrates how to solve the water jug problem using reinforcement learning. It is a modification of the Simple Water Jug Agent. Two main changes are made: templates are used to generate the full space of possible moves that the agent can perform and rewards are set based on the problem solution.

    Soar capabilities
    • Reinforcement learning
    Download LinksExternal Environment
    • None.
    Default Rules
    • None.
    Associated Publications
    • The
    ...
    See more | Go to post

  • Water Jug (Hierarchical Task Decomposition)

    Water Jug (Hierarchical Task Decomposition)

    This project contains a version of the water jug problem that is formulated for hierarchical task decomposition. It involves two levels of problem spaces. The top level has three operators: fill, empty or pour. The next level consists of three operators: pick-up, fill-jug and put-down and they arise in an operator no-change for the super state.

    Note: This agent works with chunking, which compiles the actions in the substates into rules that apply at the top-state. Use the command "learn...
    See more | Go to post

  • Water Jug (Look-Ahead with State Evaluation)

    Water Jug (Look-Ahead with State Evaluation)

    This agent is a modification of the Water Jug Simple Agent that demonstrates using a tie impasse to subgoal and evaluate operators. This is an excellent demonstration of look-ahead search and how the selection default rules work.

    Unlike the Water Jug Look-Ahead Agent, the tie agent has knowledge that prefers certain moves over others, for example preferring a pour after a fill operator, so it is able to solve the problem much more efficiently.

    Soar capabilities
    • Look-ahead
    ...
    See more | Go to post

  • Water Jug (Look-Ahead)

    Water Jug (Look-Ahead)

    This agent is a modification of the Water Jug Simple Agent that demonstrates using a tie impasse to subgoal and evaluate operators. This is an excellent demonstration of look-ahead search and how the selection default rules work.

    Unlike the Water Jug Look-Ahead Agent with State Evaluation , the look-ahead agent has no knowledge that prefers certain moves over others, so it does exhaustive search which takes far more decision cycles.

    Soar capabilities
    • Look-ahead subgo
    ...
    See more | Go to post

  • Water Jug (Simple)

    Water Jug (Simple)

    These Soar productions implement the water-jug task. The task is to find the sequence of steps that fill the three gallon jug with one gallon of water. There are a well that has an infinite amount of water, a five gallon jug, and a three gallon jug.

    The task problem space has three operators: empty, fill, and pour. Empty empties a jug into the well. Fill fills up a jug from the well. Pour pours some or all of the contents from one jug into the other jug. Pour can only pour out the contents...
    See more | Go to post
Working...
X