bazald's Publications

  1. Mitchell Keith Bloch. Automatic Value Function Refinement and Unrefinement for Relational Reinforcement Learning. The 36th Soar Workshop, 2016. (Soar Group Mirror)
  2. Mitchell Keith Bloch and John Edwin Laird. The Carli Architecture—Efficient Value Function Specialization for Relational Reinforcement Learning. Reinforcement Learning and Decision Making Meetings 2015, Extended Abstract M24, pages 44-47. (RLDM2015 Mirror) [Poster]
  3. Mitchell Keith Bloch. Implementing GQ(λ) for RL in Soar. The 35th Soar Workshop, 2015. (Soar Group Mirror)
  4. Mitchell Keith Bloch. Relational Blocks World Experiments in Carli. The 35th Soar Workshop, 2015. (Soar Group Mirror)
  5. Mitchell Keith Bloch. Value Function Representation: Rete for Reinforcement Learning. The 34th Soar Workshop, 2014. (Soar Group Mirror)
  6. Mitchell Keith Bloch and John Edwin Laird. Online Value Function Improvement. Reinforcement Learning and Decision Making Meetings 2013, Extended Abstract S32, pages 111-115. (RLDM2013 Mirror) [Poster]
  7. Mitchell Keith Bloch. Online Value Function Improvement. The 33rd Soar Workshop, 2013. (Soar Group Mirror)
  8. Mitchell Keith Bloch. Heuristic Value Function Revision. The 32nd Soar Workshop, 2012. (Soar Group Mirror)
  9. Mitchell Keith Bloch. Improving Off-Policy Hierarchical Reinforcement Learning in Soar. The 31st Soar Workshop, 2011. (Soar Group Mirror)
  10. Mitchell Keith Bloch. MAXQ Hierarchical Reinforcement Learning in Soar. The 30th Soar Workshop, 2010. (Soar Group Mirror)
  11. Mitchell Keith Bloch. Hierarchical Reinforcement Learning in the Taxicab Domain. Technical Report Number CCA-TR-2009-02. Ann Arbor, MI: Center for Cognitive Architecture, University of Michigan, 2009. (Soar Group Mirror)
  12. Mitchell Keith Bloch. Hierarchical Reinforcement Learning in the Taxicab Domain. The 29th Soar Workshop, 2009. (Soar Group Mirror)