Matches in SemOpenAlex for { <https://semopenalex.org/work/W2471420078> ?p ?o ?g. }
- W2471420078 abstract "Real-world planning problems often feature multiple sources of uncertainty, including randomness in outcomes, the presence of adversarial agents, and lack of complete knowledge of the world state. This thesis describes algorithms for four related formal models that can address multiple types of uncertainty: Markov decision processes, MDPs with adversarial costs, extensive-form games, and a new class of games that includes both extensive-form games and MDPs as special cases. Markov decision processes can represent problems where actions have stochastic outcomes. We describe several new algorithms for MDPs, and then show how MDPs can be generalized to model the presence of an adversary that has some control over costs. Extensive-form games can model games with random events and partial observability. In the zero-sum perfect-recall case, a minimax solution can be found in time polynomial in the size of the game tree. However, the game tree must all past actions and random outcomes, and so the size of the game tree grows exponentially in the length of the game. This thesis introduces a new generalization of extensive-form games that relaxes this need to remember all past actions exactly, producing exponentially smaller representations for interesting problems. Further, this formulation unifies extensive-form games with MOP planning. We present a new class of fast anytime algorithms for the off-line computation of minimax equilibria in both traditional and generalized extensive-form games. Experimental results demonstrate their effectiveness on an adversarial MDP problem and on a large abstracted poker game. We also present a new algorithm for playing repeated extensive-form games that can be used when only the total payoff of the game is observed on each round." @default.
- W2471420078 created "2016-07-22" @default.
- W2471420078 creator A5012830032 @default.
- W2471420078 creator A5024803432 @default.
- W2471420078 creator A5040311844 @default.
- W2471420078 date "2006-01-01" @default.
- W2471420078 modified "2023-09-23" @default.
- W2471420078 title "Robust planning in domains with stochastic outcomes, adversaries, and partial observability" @default.
- W2471420078 cites W108082272 @default.
- W2471420078 cites W141456974 @default.
- W2471420078 cites W1480317510 @default.
- W2471420078 cites W1483269863 @default.
- W2471420078 cites W1506832649 @default.
- W2471420078 cites W1542941925 @default.
- W2471420078 cites W1553702074 @default.
- W2471420078 cites W1569054662 @default.
- W2471420078 cites W1572411218 @default.
- W2471420078 cites W1575658237 @default.
- W2471420078 cites W1576452626 @default.
- W2471420078 cites W1664963465 @default.
- W2471420078 cites W1835254890 @default.
- W2471420078 cites W1908253641 @default.
- W2471420078 cites W1963964297 @default.
- W2471420078 cites W1968703966 @default.
- W2471420078 cites W1971443646 @default.
- W2471420078 cites W1980717955 @default.
- W2471420078 cites W1992876208 @default.
- W2471420078 cites W1993711637 @default.
- W2471420078 cites W1998191601 @default.
- W2471420078 cites W2002285507 @default.
- W2471420078 cites W2010997912 @default.
- W2471420078 cites W2014482607 @default.
- W2471420078 cites W2023373582 @default.
- W2471420078 cites W2028145673 @default.
- W2471420078 cites W2032029137 @default.
- W2471420078 cites W2044121814 @default.
- W2471420078 cites W2048226872 @default.
- W2471420078 cites W2049543502 @default.
- W2471420078 cites W2052602889 @default.
- W2471420078 cites W2062567558 @default.
- W2471420078 cites W2077902449 @default.
- W2471420078 cites W2079557194 @default.
- W2471420078 cites W2081328787 @default.
- W2471420078 cites W2085245641 @default.
- W2471420078 cites W2097477220 @default.
- W2471420078 cites W2098432798 @default.
- W2471420078 cites W2114245943 @default.
- W2471420078 cites W2116067849 @default.
- W2471420078 cites W2116753650 @default.
- W2471420078 cites W2122187689 @default.
- W2471420078 cites W2134396776 @default.
- W2471420078 cites W2134802714 @default.
- W2471420078 cites W2136558412 @default.
- W2471420078 cites W2144508386 @default.
- W2471420078 cites W2148825261 @default.
- W2471420078 cites W2159420891 @default.
- W2471420078 cites W2165357696 @default.
- W2471420078 cites W2168359464 @default.
- W2471420078 cites W2170120409 @default.
- W2471420078 cites W2170408876 @default.
- W2471420078 cites W2296319761 @default.
- W2471420078 cites W2296620075 @default.
- W2471420078 cites W2341171179 @default.
- W2471420078 cites W2498386205 @default.
- W2471420078 cites W292627938 @default.
- W2471420078 cites W3023115439 @default.
- W2471420078 cites W3123286829 @default.
- W2471420078 cites W3145128584 @default.
- W2471420078 cites W2522081855 @default.
- W2471420078 hasPublicationYear "2006" @default.
- W2471420078 type Work @default.
- W2471420078 sameAs 2471420078 @default.
- W2471420078 citedByCount "7" @default.
- W2471420078 countsByYear W24714200782012 @default.
- W2471420078 countsByYear W24714200782014 @default.
- W2471420078 countsByYear W24714200782015 @default.
- W2471420078 crossrefType "journal-article" @default.
- W2471420078 hasAuthorship W2471420078A5012830032 @default.
- W2471420078 hasAuthorship W2471420078A5024803432 @default.
- W2471420078 hasAuthorship W2471420078A5040311844 @default.
- W2471420078 hasConcept C105795698 @default.
- W2471420078 hasConcept C106189395 @default.
- W2471420078 hasConcept C114073186 @default.
- W2471420078 hasConcept C125112378 @default.
- W2471420078 hasConcept C126255220 @default.
- W2471420078 hasConcept C134306372 @default.
- W2471420078 hasConcept C149728462 @default.
- W2471420078 hasConcept C154945302 @default.
- W2471420078 hasConcept C159886148 @default.
- W2471420078 hasConcept C177148314 @default.
- W2471420078 hasConcept C2777212361 @default.
- W2471420078 hasConcept C28826006 @default.
- W2471420078 hasConcept C33923547 @default.
- W2471420078 hasConcept C36299963 @default.
- W2471420078 hasConcept C37736160 @default.
- W2471420078 hasConcept C41008148 @default.
- W2471420078 hasConcept C80444323 @default.
- W2471420078 hasConceptScore W2471420078C105795698 @default.
- W2471420078 hasConceptScore W2471420078C106189395 @default.
- W2471420078 hasConceptScore W2471420078C114073186 @default.