Содержание
- 2. Classical Approaches to Planning Classical Planning
- 3. Planning with Hierarchical Task Networks HTN Planning
- 4. Classical and HTN Planning Challenge: Can we unify classical and HTN planning in a single framework?
- 5. Mixed Classical / HTN Planning HTN Planning impasse? Classical Planning yes no
- 6. Learning HTNs from Classical Planning HTN Planning impasse? Classical Planning yes no HTN Learning
- 7. Four Contributions of the Research Representation: A specialized class of hierarchical task nets. Execution: A reactive
- 8. A New Representational Formalism Concepts: A set of conjunctive relational inference rules; Primitive skills: A set
- 9. Some Defined Concepts (Axioms) (clear (?block) :percepts ((block ?block)) :negatives ((on ?other ?block))) (hand-empty ( )
- 10. Some Primitive Skills (Operators) (unstack (?block ?from) :percepts ((block ?block ypos ?ypos) (block ?from)) :start (unstackable
- 11. Some NonPrimitive Recursive Skills (clear (?C) :percepts ((block ?D) (block ?C)) :start (unstackable ?D ?C) :skills
- 12. Interleaving HTN Execution and Classical Planning Solve(G) Push the goal literal G onto the empty goal
- 13. A Successful Planning Trace (ontable A T) (on B A) (on C B) (hand-empty) (clear C)
- 14. Three Questions about HTN Learning What is the hierarchical structure of the network? What are the
- 15. Recording Results for Learning Solve(G) Push the goal literal G onto the empty goal stack GS.
- 16. Three Questions about HTN Learning What is the hierarchical structure of the network? The structure is
- 17. (ontable A T) (on B A) (on C B) (hand-empty) (clear C) (unst. C B) (unstack
- 18. (ontable A T) (on B A) (on C B) (hand-empty) (clear C) (unst. C B) (unstack
- 19. (ontable A T) (on B A) (on C B) (hand-empty) (clear C) (unst. C B) (unstack
- 20. (ontable A T) (on B A) (on C B) (hand-empty) (clear C) (unst. C B) (unstack
- 21. Learned Skills After Structure Determined ( (?C) :percepts ((block ?D) (block ?C)) :start :skills ((unstack ?D
- 22. Three Questions about HTN Learning What is the hierarchical structure of the network? The structure is
- 23. Learned Skills After Heads Inserted (clear (?C) :percepts ((block ?D) (block ?C)) :start :skills ((unstack ?D
- 24. Three Questions about HTN Learning What is the hierarchical structure of the network? The structure is
- 25. Learned Skills After Conditions Inferred (clear (?C) :percepts ((block ?D) (block ?C)) :start (unstackable ?D ?C)
- 26. Learning an HTN Method from a Problem Solution Learn(G) If the goal G involves skill chaining,
- 27. Creating a Clause from Skill Chaining Problem Solution New Method
- 28. Creating a Clause from Concept Chaining Problem Solution New Method
- 29. Important Features of Learning Method it occurs incrementally from one experience at a time; it takes
- 30. An In-City Driving Environment Our focus on learning for reactive control comes from an interest in
- 31. Skill Clauses Learning for In-City Driving parked (?ME ?G1152) :percepts ( (lane-line ?G1152) (self ?ME)) :start
- 32. Learning Curves for In-City Driving
- 33. Transfer Studies of HTN Learning Because we were interested in our method’s ability to transfer its
- 34. Transfer Effects in the Blocks World On 20-block tasks, there is no difference in solved problems.
- 35. Transfer Effects in the Blocks World However, there is difference in the effort needed to solve
- 36. FreeCell Solitaire FreeCell is a full-information card game that, in most cases, can be solved by
- 37. Transfer Effects in FreeCell On 16-card FreeCell tasks, prior training aids solution probability. 16 cards
- 38. Transfer Effects in FreeCell However, it also lets the system solve problems with less effort. 16
- 39. Transfer Effects in FreeCell On 20-card tasks, the benefits of prior training are much stronger. 20
- 40. Transfer Effects in FreeCell However, it also lets the system solve problems with less effort. 20
- 41. Where is the Utility Problem? Many previous studies of learning and planning found that: learned knowledge
- 42. Related Work on Planning and Execution problem-solving architectures like Soar and Prodigy Nilsson’s (1994) notion of
- 43. Related Research on Learning production composition (e.g., Neves & Anderson, 1981) macro-operator formation (e.g., Iba, 1985)
- 44. The ICARUS Architecture Long-Term Conceptual Memory Long-Term Skill Memory Short-Term Conceptual Memory Goal/Skill Stack Categorization and
- 45. Hierarchical Structure of Long-Term Memory concepts skills Each concept is defined in terms of other concepts
- 46. Interleaved Nature of Long-Term Memory For example, the skill highlighted here refers directly to the highlighted
- 47. Recognizing Concepts and Selecting Skills concepts skills Concepts are matched bottom up, starting from percepts. Skill
- 48. Directions for Future Work Despite our initial progress on structure learning, we should still: evaluate approach
- 49. relies on a new formalism – teleoreactive logic programs – that identifies heads with goals and
- 51. Скачать презентацию