Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033564068> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3033564068 abstract "Throughout scientific history, overarching theoretical frameworks have allowed researchers to grow beyond personal intuitions and culturally biased theories. They allow to verify and replicate existing findings, and to link is connected results. The notion of self-play, albeit often cited in multiagent Reinforcement Learning, has never been grounded in a formal model. We present a formalized framework, with clearly defined assumptions, which encapsulates the meaning of self-play as abstracted from various existing self-play algorithms. This framework is framed as an approximation to a theoretical solution concept for multiagent training. On a simple environment, we qualitatively measure how well a subset of the captured self-play methods approximate this solution when paired with the famous PPO algorithm. We also provide insights on interpreting quantitative metrics of performance for self-play training. Our results indicate that, throughout training, various self-play definitions exhibit cyclic policy evolutions." @default.
- W3033564068 created "2020-06-12" @default.
- W3033564068 creator A5017600718 @default.
- W3033564068 creator A5033216620 @default.
- W3033564068 creator A5048451922 @default.
- W3033564068 creator A5068468650 @default.
- W3033564068 creator A5088454205 @default.
- W3033564068 date "2020-06-08" @default.
- W3033564068 modified "2023-09-27" @default.
- W3033564068 title "A Comparison of Self-Play Algorithms Under a Generalized Framework" @default.
- W3033564068 cites W1579184372 @default.
- W3033564068 cites W164946830 @default.
- W3033564068 cites W2107649750 @default.
- W3033564068 cites W2187089797 @default.
- W3033564068 cites W2201581102 @default.
- W3033564068 cites W2618097077 @default.
- W3033564068 cites W2736601468 @default.
- W3033564068 cites W2762872434 @default.
- W3033564068 cites W2772709170 @default.
- W3033564068 cites W2810602713 @default.
- W3033564068 cites W2919720931 @default.
- W3033564068 cites W2973736687 @default.
- W3033564068 cites W2976996772 @default.
- W3033564068 cites W2977093897 @default.
- W3033564068 cites W2982316857 @default.
- W3033564068 cites W3198350258 @default.
- W3033564068 cites W2131600418 @default.
- W3033564068 hasPublicationYear "2020" @default.
- W3033564068 type Work @default.
- W3033564068 sameAs 3033564068 @default.
- W3033564068 citedByCount "2" @default.
- W3033564068 countsByYear W30335640682020 @default.
- W3033564068 countsByYear W30335640682021 @default.
- W3033564068 crossrefType "posted-content" @default.
- W3033564068 hasAuthorship W3033564068A5017600718 @default.
- W3033564068 hasAuthorship W3033564068A5033216620 @default.
- W3033564068 hasAuthorship W3033564068A5048451922 @default.
- W3033564068 hasAuthorship W3033564068A5068468650 @default.
- W3033564068 hasAuthorship W3033564068A5088454205 @default.
- W3033564068 hasConcept C105795698 @default.
- W3033564068 hasConcept C111472728 @default.
- W3033564068 hasConcept C11413529 @default.
- W3033564068 hasConcept C124101348 @default.
- W3033564068 hasConcept C138885662 @default.
- W3033564068 hasConcept C154945302 @default.
- W3033564068 hasConcept C2780009758 @default.
- W3033564068 hasConcept C2780586882 @default.
- W3033564068 hasConcept C2780876879 @default.
- W3033564068 hasConcept C2781162219 @default.
- W3033564068 hasConcept C33923547 @default.
- W3033564068 hasConcept C41008148 @default.
- W3033564068 hasConcept C97541855 @default.
- W3033564068 hasConceptScore W3033564068C105795698 @default.
- W3033564068 hasConceptScore W3033564068C111472728 @default.
- W3033564068 hasConceptScore W3033564068C11413529 @default.
- W3033564068 hasConceptScore W3033564068C124101348 @default.
- W3033564068 hasConceptScore W3033564068C138885662 @default.
- W3033564068 hasConceptScore W3033564068C154945302 @default.
- W3033564068 hasConceptScore W3033564068C2780009758 @default.
- W3033564068 hasConceptScore W3033564068C2780586882 @default.
- W3033564068 hasConceptScore W3033564068C2780876879 @default.
- W3033564068 hasConceptScore W3033564068C2781162219 @default.
- W3033564068 hasConceptScore W3033564068C33923547 @default.
- W3033564068 hasConceptScore W3033564068C41008148 @default.
- W3033564068 hasConceptScore W3033564068C97541855 @default.
- W3033564068 hasLocation W30335640681 @default.
- W3033564068 hasOpenAccess W3033564068 @default.
- W3033564068 hasPrimaryLocation W30335640681 @default.
- W3033564068 hasRelatedWork W1044706469 @default.
- W3033564068 hasRelatedWork W1598854325 @default.
- W3033564068 hasRelatedWork W1858620475 @default.
- W3033564068 hasRelatedWork W208029328 @default.
- W3033564068 hasRelatedWork W2107516609 @default.
- W3033564068 hasRelatedWork W2141454839 @default.
- W3033564068 hasRelatedWork W2158093450 @default.
- W3033564068 hasRelatedWork W2417727340 @default.
- W3033564068 hasRelatedWork W2528826067 @default.
- W3033564068 hasRelatedWork W2588243137 @default.
- W3033564068 hasRelatedWork W2998739343 @default.
- W3033564068 hasRelatedWork W2999616218 @default.
- W3033564068 hasRelatedWork W3004897372 @default.
- W3033564068 hasRelatedWork W3008509023 @default.
- W3033564068 hasRelatedWork W3082674211 @default.
- W3033564068 hasRelatedWork W3088236484 @default.
- W3033564068 hasRelatedWork W3156735127 @default.
- W3033564068 hasRelatedWork W889081164 @default.
- W3033564068 hasRelatedWork W115804501 @default.
- W3033564068 hasRelatedWork W1530008426 @default.
- W3033564068 isParatext "false" @default.
- W3033564068 isRetracted "false" @default.
- W3033564068 magId "3033564068" @default.
- W3033564068 workType "article" @default.