Statements (66)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
algorithm
|
| gptkbp:appliesTo |
planning
reinforcement learning game playing |
| gptkbp:completed |
state-of-the-art performance
|
| gptkbp:developedBy |
DeepMind
|
| gptkbp:hasCapital |
playing board games
playing_Atari_games |
| gptkbp:hasCollaboratedWith |
various academic institutions
|
| gptkbp:hasPerformedAt |
conferences
|
| gptkbp:hasRelatedPatent |
robotics
AI research game_AI |
| https://www.w3.org/2000/01/rdf-schema#label |
MuZero
|
| gptkbp:isActiveIn |
research papers
case studies |
| gptkbp:isAttendedBy |
research labs
industry practitioners |
| gptkbp:isAvenueFor |
gptkb:AlphaZero
|
| gptkbp:isBasedOn |
Monte Carlo Tree Search
reinforcement learning principles |
| gptkbp:isCitedIn |
academic papers
|
| gptkbp:isDesignedFor |
model-based reinforcement learning
|
| gptkbp:isDiscussedIn |
AI forums
|
| gptkbp:isDocumentedIn |
technical reports
|
| gptkbp:isEvaluatedBy |
Go
performance metrics human players peer reviews chess Shogi comparison studies |
| gptkbp:isExploredIn |
thesis papers
AI literature |
| gptkbp:isInfluencedBy |
AI development
previous work in AI |
| gptkbp:isKnownFor |
high performance
robustness adaptability sample efficiency flexibility in environments generalization capabilities |
| gptkbp:isNotableFor |
combining planning and learning
|
| gptkbp:isPartOf |
gptkb:AlphaGo
AlphaStar DQN DeepMind's research portfolio DeepMind's AI advancements |
| gptkbp:isPublishedIn |
scientific journals
|
| gptkbp:isRecognizedBy |
AI community
|
| gptkbp:isRecognizedFor |
innovative approach
|
| gptkbp:isReferencedIn |
AI textbooks
|
| gptkbp:isStudiedIn |
graduate courses
|
| gptkbp:isSupportedBy |
collaborative projects
open-source implementations extensive research funding |
| gptkbp:isTestedFor |
real-world scenarios
simulated environments |
| gptkbp:isTrainedIn |
various benchmarks
other algorithms |
| gptkbp:isUtilizedIn |
AI competitions
|
| gptkbp:isVisitedBy |
complex decision making
|
| gptkbp:learnsMove |
environment dynamics
|
| gptkbp:uses |
temporal difference learning
|
| gptkbp:utilizes |
neural networks
|
| gptkbp:wasAffecting |
2019
|