David Bourget (Western Ontario)
David Chalmers (ANU, NYU)
Rafael De Clercq
Jack Alan Reynolds
Learn more about PhilPapers
This paper is concerned with autonomous learning of plans in probabilistic domains without a priori domain-specific knowledge. In contrast to existing reinforcement learning algorithms that generate only reactive plans and existing probabilistic planning algorithms that require a substantial amount of a priori knowledge in order to plan, a two-stage bottom-up process is devised, in which first reinforcement learning/dynamic programming is applied, without the use of a priori domain-specific knowledge, to acquire a reactive plan and then explicit plans are extracted from the reactive plan. Several options for plan extraction are examined, each of which is based on a beam search that performs temporal projection in a restricted fashion, guided by the value functions resulting from reinforcement learning/dynamic programming. Some completeness and soundness results are given. Examples in several domains are discussed that together demonstrate the working of the proposed model
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
|Through your library||Only published papers are available at libraries|
Similar books and articles
Ron Sun, Beyond Simple Rule Extraction: The Extraction of Planning Knowledge From Reinforcement Learners.
Edward Merrillb & Todd Petersonb (2001). From Implicit Skills to Explicit Knowledge: A Bottom‐Up Model of Skill Learning. Cognitive Science 25 (2):203-244.
Ron Sun, Todd Peterson & Edward Merrill, Bottom-Up Skill Learning in Reactive Sequential Decision Tasks.
Tuomas E. Tahko (2011). A Priori and A Posteriori: A Bootstrapping Relationship. Metaphysica 12 (2):151-164.
Daniel John Zizzo (2000). Implicit Learning of (Boundedly) Rational Behaviour. Behavioral and Brain Sciences 23 (5):700-701.
Added to index2012-09-05
Total downloads5 ( #175,815 of 1,004,646 )
Recent downloads (6 months)1 ( #64,617 of 1,004,646 )
How can I increase my downloads?