FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805855679> ?p ?o ?g. }

• W2805855679 endingPage "79" @default.
• W2805855679 startingPage "46" @default.
• W2805855679 abstract "Teaching computer programs to play games through machine learning has been an important way to achieve better artificial intelligence (AI) in a variety of real-world applications. Monte Carlo Tree Search (MCTS) is one of the key AI techniques developed recently that enabled AlphaGo to defeat a legendary professional Go player. What makes MCTS particularly attractive is that it only understands the basic rules of the game and does not rely on expert-level knowledge. Researchers thus expect that MCTS can be applied to other complex AI problems where domain-specific expert-level knowledge is not yet available. So far there are very few analytic studies in the literature. In this paper, our goal is to develop analytic studies of MCTS to build a more fundamental understanding of the algorithms and their applicability in complex AI problems. We start with a simple version of MCTS, called random playout search (RPS), to play Tic-Tac-Toe, and find that RPS may fail to discover the correct moves even in a very simple game position of Tic-Tac-Toe. Both the probability analysis and simulation have confirmed our discovery. We continue our studies with the full version of MCTS to play Gomoku and find that while MCTS has shown great success in playing more sophisticated games like Go, it is not effective to address the problem of sudden death/win. The main reason that MCTS often fails to detect sudden death/win lies in the random playout search nature of MCTS, which leads to prediction distortion. Therefore, although MCTS in theory converges to the optimal minimax search, with real world computational resource constraints, MCTS has to rely on RPS as an important step in its search process, therefore suffering from the same fundamental prediction distortion problem as RPS does. By examining the detailed statistics of the scores in MCTS, we investigate a variety of scenarios where MCTS fails to detect sudden death/win. Finally, we propose an improved MCTS algorithm by incorporating minimax search to overcome prediction distortion. Our simulation has confirmed the effectiveness of the proposed algorithm. We provide an estimate of the additional computational costs of this new algorithm to detect sudden death/win and discuss heuristic strategies to further reduce the search complexity." @default.
• W2805855679 created "2018-06-13" @default.
• W2805855679 creator A5072161328 @default.
• W2805855679 date "2018-01-01" @default.
• W2805855679 modified "2023-10-18" @default.
• W2805855679 title "Prediction Distortion in Monte Carlo Tree Search and an Improved Algorithm" @default.
• W2805855679 cites W1625390266 @default.
• W2805855679 cites W1714211023 @default.
• W2805855679 cites W1968887996 @default.
• W2805855679 cites W1999536101 @default.
• W2805855679 cites W2016647253 @default.
• W2805855679 cites W2126316555 @default.
• W2805855679 cites W2143610817 @default.
• W2805855679 cites W2295465200 @default.
• W2805855679 cites W2618342356 @default.
• W2805855679 cites W2766447205 @default.
• W2805855679 cites W2775046486 @default.
• W2805855679 doi "https://doi.org/10.4236/jilsa.2018.102004" @default.
• W2805855679 hasPublicationYear "2018" @default.
• W2805855679 type Work @default.
• W2805855679 sameAs 2805855679 @default.
• W2805855679 citedByCount "2" @default.
• W2805855679 countsByYear W28058556792021 @default.
• W2805855679 crossrefType "journal-article" @default.
• W2805855679 hasAuthorship W2805855679A5072161328 @default.
• W2805855679 hasBestOaLocation W28058556791 @default.
• W2805855679 hasConcept C105795698 @default.
• W2805855679 hasConcept C111472728 @default.
• W2805855679 hasConcept C113174947 @default.
• W2805855679 hasConcept C11413529 @default.
• W2805855679 hasConcept C119857082 @default.
• W2805855679 hasConcept C125583679 @default.
• W2805855679 hasConcept C126780896 @default.
• W2805855679 hasConcept C134306372 @default.
• W2805855679 hasConcept C136197465 @default.
• W2805855679 hasConcept C138885662 @default.
• W2805855679 hasConcept C154945302 @default.
• W2805855679 hasConcept C162324750 @default.
• W2805855679 hasConcept C175444787 @default.
• W2805855679 hasConcept C177142836 @default.
• W2805855679 hasConcept C194257627 @default.
• W2805855679 hasConcept C19499675 @default.
• W2805855679 hasConcept C207685749 @default.
• W2805855679 hasConcept C26517878 @default.
• W2805855679 hasConcept C2776257435 @default.
• W2805855679 hasConcept C2780586882 @default.
• W2805855679 hasConcept C31258907 @default.
• W2805855679 hasConcept C33923547 @default.
• W2805855679 hasConcept C36503486 @default.
• W2805855679 hasConcept C38652104 @default.
• W2805855679 hasConcept C41008148 @default.
• W2805855679 hasConcept C46149586 @default.
• W2805855679 hasConcept C73795354 @default.
• W2805855679 hasConcept C95815963 @default.
• W2805855679 hasConceptScore W2805855679C105795698 @default.
• W2805855679 hasConceptScore W2805855679C111472728 @default.
• W2805855679 hasConceptScore W2805855679C113174947 @default.
• W2805855679 hasConceptScore W2805855679C11413529 @default.
• W2805855679 hasConceptScore W2805855679C119857082 @default.
• W2805855679 hasConceptScore W2805855679C125583679 @default.
• W2805855679 hasConceptScore W2805855679C126780896 @default.
• W2805855679 hasConceptScore W2805855679C134306372 @default.
• W2805855679 hasConceptScore W2805855679C136197465 @default.
• W2805855679 hasConceptScore W2805855679C138885662 @default.
• W2805855679 hasConceptScore W2805855679C154945302 @default.
• W2805855679 hasConceptScore W2805855679C162324750 @default.
• W2805855679 hasConceptScore W2805855679C175444787 @default.
• W2805855679 hasConceptScore W2805855679C177142836 @default.
• W2805855679 hasConceptScore W2805855679C194257627 @default.
• W2805855679 hasConceptScore W2805855679C19499675 @default.
• W2805855679 hasConceptScore W2805855679C207685749 @default.
• W2805855679 hasConceptScore W2805855679C26517878 @default.
• W2805855679 hasConceptScore W2805855679C2776257435 @default.
• W2805855679 hasConceptScore W2805855679C2780586882 @default.
• W2805855679 hasConceptScore W2805855679C31258907 @default.
• W2805855679 hasConceptScore W2805855679C33923547 @default.
• W2805855679 hasConceptScore W2805855679C36503486 @default.
• W2805855679 hasConceptScore W2805855679C38652104 @default.
• W2805855679 hasConceptScore W2805855679C41008148 @default.
• W2805855679 hasConceptScore W2805855679C46149586 @default.
• W2805855679 hasConceptScore W2805855679C73795354 @default.
• W2805855679 hasConceptScore W2805855679C95815963 @default.
• W2805855679 hasIssue "02" @default.
• W2805855679 hasLocation W28058556791 @default.
• W2805855679 hasOpenAccess W2805855679 @default.
• W2805855679 hasPrimaryLocation W28058556791 @default.
• W2805855679 hasRelatedWork W1521379096 @default.
• W2805855679 hasRelatedWork W1968887996 @default.
• W2805855679 hasRelatedWork W2065339974 @default.
• W2805855679 hasRelatedWork W2112583639 @default.
• W2805855679 hasRelatedWork W2188928203 @default.
• W2805855679 hasRelatedWork W2563083044 @default.
• W2805855679 hasRelatedWork W2978000411 @default.
• W2805855679 hasRelatedWork W3171665292 @default.
• W2805855679 hasRelatedWork W4293919576 @default.
• W2805855679 hasRelatedWork W4327811054 @default.
• W2805855679 hasVolume "10" @default.
• W2805855679 isParatext "false" @default.

• next