This agent contains a version of blocks-world that involves one level of problem spaces and look-ahead but with two important extensions. It demonstrates how RL-rules can be learned by chunking and then updated in the future. The advantage over simple lookahead is that it doesn't lock on to the one path found during look-ahead after chunking. It will still do some exploration.

Soar capabilities
  • Reinforcement Learning
  • Chunking
  • Look-ahead Subgoaling
  • Can learn procedural knowledge (enable with 'learn always')
Download Links
External Environment
  • None.
Default Rules
  • simple.soar
  • selection.soar
Associated PublicationsDeveloper
  • John Laird
Soar Versions
  • Soar 8,9
Project Type
  • VisualSoar