Matches in SemOpenAlex for { <https://semopenalex.org/work/W12755008> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W12755008 endingPage "48" @default.
- W12755008 startingPage "42" @default.
- W12755008 abstract "The Factored Policy-Gradient planner (FPG) (Buffet & Aberdeen 2006) was a successful competitor in the probabilistic track of the 2006 International Planning Competition (IPC). FPG is innovative because it scales to large planning domains through the use of Reinforcement Learning. It essentially performs a stochastic local search in policy space. FPG's weakness is potentially long learning times, as it initially acts randomly and progressively improves its policy each time the goal is reached. This paper shows how to use an external teacher to guide FPG's exploration. While any teacher can be used, we concentrate on the actions suggested by FF's heuristic (Hoffmann 2001), as FF-replan has proved efficient for probabilistic re-planning. To achieve this, FPG must learn its own policy while following another. We thus extend FPG to off-policy learning using importance sampling (Glynn & Iglehart 1989; Peshkin & Shelton 2002). The resulting algorithm is presented and evaluated on IPC benchmarks." @default.
- W12755008 created "2016-06-24" @default.
- W12755008 creator A5015132137 @default.
- W12755008 creator A5022343068 @default.
- W12755008 date "2007-09-22" @default.
- W12755008 modified "2023-09-30" @default.
- W12755008 title "FF+FPG: guiding a policy-gradient planner" @default.
- W12755008 cites W115173043 @default.
- W12755008 cites W127341816 @default.
- W12755008 cites W1501637551 @default.
- W12755008 cites W1545688112 @default.
- W12755008 cites W1596364083 @default.
- W12755008 cites W1814308503 @default.
- W12755008 cites W2033976720 @default.
- W12755008 cites W2087018957 @default.
- W12755008 cites W2097083865 @default.
- W12755008 cites W2119717200 @default.
- W12755008 cites W2126902640 @default.
- W12755008 cites W2128547596 @default.
- W12755008 cites W2147632348 @default.
- W12755008 cites W2253356247 @default.
- W12755008 cites W3020882730 @default.
- W12755008 cites W39100366 @default.
- W12755008 hasPublicationYear "2007" @default.
- W12755008 type Work @default.
- W12755008 sameAs 12755008 @default.
- W12755008 citedByCount "12" @default.
- W12755008 countsByYear W127550082012 @default.
- W12755008 countsByYear W127550082015 @default.
- W12755008 countsByYear W127550082019 @default.
- W12755008 crossrefType "proceedings-article" @default.
- W12755008 hasAuthorship W12755008A5015132137 @default.
- W12755008 hasAuthorship W12755008A5022343068 @default.
- W12755008 hasConcept C119857082 @default.
- W12755008 hasConcept C154945302 @default.
- W12755008 hasConcept C173801870 @default.
- W12755008 hasConcept C18903297 @default.
- W12755008 hasConcept C2776999362 @default.
- W12755008 hasConcept C2779436431 @default.
- W12755008 hasConcept C33923547 @default.
- W12755008 hasConcept C41008148 @default.
- W12755008 hasConcept C42475967 @default.
- W12755008 hasConcept C49937458 @default.
- W12755008 hasConcept C86803240 @default.
- W12755008 hasConcept C91306197 @default.
- W12755008 hasConcept C97541855 @default.
- W12755008 hasConceptScore W12755008C119857082 @default.
- W12755008 hasConceptScore W12755008C154945302 @default.
- W12755008 hasConceptScore W12755008C173801870 @default.
- W12755008 hasConceptScore W12755008C18903297 @default.
- W12755008 hasConceptScore W12755008C2776999362 @default.
- W12755008 hasConceptScore W12755008C2779436431 @default.
- W12755008 hasConceptScore W12755008C33923547 @default.
- W12755008 hasConceptScore W12755008C41008148 @default.
- W12755008 hasConceptScore W12755008C42475967 @default.
- W12755008 hasConceptScore W12755008C49937458 @default.
- W12755008 hasConceptScore W12755008C86803240 @default.
- W12755008 hasConceptScore W12755008C91306197 @default.
- W12755008 hasConceptScore W12755008C97541855 @default.
- W12755008 hasLocation W127550081 @default.
- W12755008 hasOpenAccess W12755008 @default.
- W12755008 hasPrimaryLocation W127550081 @default.
- W12755008 hasRelatedWork W127341816 @default.
- W12755008 hasRelatedWork W1530444831 @default.
- W12755008 hasRelatedWork W1545688112 @default.
- W12755008 hasRelatedWork W2009533501 @default.
- W12755008 hasRelatedWork W2105757562 @default.
- W12755008 hasRelatedWork W2128459535 @default.
- W12755008 hasRelatedWork W2156347136 @default.
- W12755008 hasRelatedWork W2243242557 @default.
- W12755008 hasRelatedWork W2780045768 @default.
- W12755008 hasRelatedWork W2792305967 @default.
- W12755008 hasRelatedWork W2807939031 @default.
- W12755008 hasRelatedWork W2995931713 @default.
- W12755008 hasRelatedWork W2996343999 @default.
- W12755008 hasRelatedWork W2996347495 @default.
- W12755008 hasRelatedWork W3022865022 @default.
- W12755008 hasRelatedWork W3032032218 @default.
- W12755008 hasRelatedWork W3036821294 @default.
- W12755008 hasRelatedWork W3210102971 @default.
- W12755008 hasRelatedWork W3210825568 @default.
- W12755008 hasRelatedWork W8422417 @default.
- W12755008 isParatext "false" @default.
- W12755008 isRetracted "false" @default.
- W12755008 magId "12755008" @default.
- W12755008 workType "article" @default.