Matches in SemOpenAlex for { <https://semopenalex.org/work/W1520928141> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W1520928141 abstract "Experience based reinforcement learning (RL) systems are known to be useful for dealing with domains that are a priori unknown. We believe that experience based methods may also be useful when the model is uncertain (or even completely known). In this case experience is gained by simulating the uncertain model. This paper explores a simple way to allow experience based RL systems to cope with uncertainty in a model. The particular form of RL we consider is a policy-gradient method. The particular domains we attempt to optimise in are from temporal decision-theoretic planning. Our previous experience with military planning problems indicates that a human specified model of the planning problem is often inaccurate, especially when humans specify probabilities, thus planners that take into account this uncertainty are very useful. Despite our focus on policy-gradient RL for planning, our simple (but approximate) solution for dealing with uncertainty in the model can be applied to any simulation based RL method, such as Q-learning or SARSA. Our attempt to solve decision-theoretic planning problems with a policy-gradient approach is novel in itself, making up another contribution of this paper." @default.
- W1520928141 created "2016-06-24" @default.
- W1520928141 creator A5015132137 @default.
- W1520928141 creator A5022343068 @default.
- W1520928141 date "2005-01-01" @default.
- W1520928141 modified "2023-09-25" @default.
- W1520928141 title "Simulation methods for uncertain decision-theoretic planning" @default.
- W1520928141 cites W108082272 @default.
- W1520928141 cites W131811946 @default.
- W1520928141 cites W1541084404 @default.
- W1520928141 cites W1590759229 @default.
- W1520928141 cites W1627367978 @default.
- W1520928141 cites W1814308503 @default.
- W1520928141 cites W192590192 @default.
- W1520928141 cites W1988217924 @default.
- W1520928141 cites W2009533501 @default.
- W1520928141 cites W2124403132 @default.
- W1520928141 cites W2138362680 @default.
- W1520928141 cites W2166476615 @default.
- W1520928141 cites W2188961590 @default.
- W1520928141 hasPublicationYear "2005" @default.
- W1520928141 type Work @default.
- W1520928141 sameAs 1520928141 @default.
- W1520928141 citedByCount "1" @default.
- W1520928141 crossrefType "proceedings-article" @default.
- W1520928141 hasAuthorship W1520928141A5015132137 @default.
- W1520928141 hasAuthorship W1520928141A5022343068 @default.
- W1520928141 hasConcept C111472728 @default.
- W1520928141 hasConcept C120665830 @default.
- W1520928141 hasConcept C121332964 @default.
- W1520928141 hasConcept C126255220 @default.
- W1520928141 hasConcept C138885662 @default.
- W1520928141 hasConcept C154945302 @default.
- W1520928141 hasConcept C192209626 @default.
- W1520928141 hasConcept C2780586882 @default.
- W1520928141 hasConcept C33923547 @default.
- W1520928141 hasConcept C41008148 @default.
- W1520928141 hasConcept C75553542 @default.
- W1520928141 hasConcept C97541855 @default.
- W1520928141 hasConceptScore W1520928141C111472728 @default.
- W1520928141 hasConceptScore W1520928141C120665830 @default.
- W1520928141 hasConceptScore W1520928141C121332964 @default.
- W1520928141 hasConceptScore W1520928141C126255220 @default.
- W1520928141 hasConceptScore W1520928141C138885662 @default.
- W1520928141 hasConceptScore W1520928141C154945302 @default.
- W1520928141 hasConceptScore W1520928141C192209626 @default.
- W1520928141 hasConceptScore W1520928141C2780586882 @default.
- W1520928141 hasConceptScore W1520928141C33923547 @default.
- W1520928141 hasConceptScore W1520928141C41008148 @default.
- W1520928141 hasConceptScore W1520928141C75553542 @default.
- W1520928141 hasConceptScore W1520928141C97541855 @default.
- W1520928141 hasLocation W15209281411 @default.
- W1520928141 hasOpenAccess W1520928141 @default.
- W1520928141 hasPrimaryLocation W15209281411 @default.
- W1520928141 hasRelatedWork W1984305926 @default.
- W1520928141 hasRelatedWork W1996040720 @default.
- W1520928141 hasRelatedWork W2027005739 @default.
- W1520928141 hasRelatedWork W2090557396 @default.
- W1520928141 hasRelatedWork W2112673402 @default.
- W1520928141 hasRelatedWork W2134154490 @default.
- W1520928141 hasRelatedWork W2371766315 @default.
- W1520928141 hasRelatedWork W2374634030 @default.
- W1520928141 hasRelatedWork W2538356301 @default.
- W1520928141 hasRelatedWork W2787732498 @default.
- W1520928141 hasRelatedWork W2789591470 @default.
- W1520928141 hasRelatedWork W2811246557 @default.
- W1520928141 hasRelatedWork W2893150977 @default.
- W1520928141 hasRelatedWork W3023248299 @default.
- W1520928141 hasRelatedWork W3026388243 @default.
- W1520928141 hasRelatedWork W3049456132 @default.
- W1520928141 hasRelatedWork W78829087 @default.
- W1520928141 hasRelatedWork W3098950901 @default.
- W1520928141 hasRelatedWork W3099314939 @default.
- W1520928141 hasRelatedWork W3151499128 @default.
- W1520928141 isParatext "false" @default.
- W1520928141 isRetracted "false" @default.
- W1520928141 magId "1520928141" @default.
- W1520928141 workType "article" @default.