Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044195506> ?p ?o ?g. }
- W3044195506 abstract "We present the Battlesnake Challenge, a framework for multi-agent reinforcement learning with Human-In-the-Loop Learning (HILL). It is developed upon Battlesnake, a multiplayer extension of the traditional Snake game in which 2 or more snakes compete for the final survival. The Battlesnake Challenge consists of an offline module for model training and an online module for live competitions. We develop a simulated game environment for the offline multi-agent model training and identify a set of baseline heuristics that can be instilled to improve learning. Our framework is agent-agnostic and heuristics-agnostic such that researchers can design their own algorithms, train their models, and demonstrate in the online Battlesnake competition. We validate the framework and baseline heuristics with our preliminary experiments. Our results show that agents with the proposed HILL methods consistently outperform agents without HILL. Besides, heuristics of reward manipulation had the best performance in the online competition. We open source our framework at this https URL." @default.
- W3044195506 created "2020-07-29" @default.
- W3044195506 creator A5011250157 @default.
- W3044195506 creator A5039829761 @default.
- W3044195506 creator A5041433085 @default.
- W3044195506 creator A5065053322 @default.
- W3044195506 date "2020-07-20" @default.
- W3044195506 modified "2023-09-25" @default.
- W3044195506 title "Battlesnake challenge: A multi-agent reinforcement learning playground with human-in-the-loop" @default.
- W3044195506 cites W1191599655 @default.
- W3044195506 cites W1542941925 @default.
- W3044195506 cites W206679605 @default.
- W3044195506 cites W2098441518 @default.
- W3044195506 cites W2099618002 @default.
- W3044195506 cites W2116157560 @default.
- W3044195506 cites W2122410182 @default.
- W3044195506 cites W2141754131 @default.
- W3044195506 cites W2145339207 @default.
- W3044195506 cites W2156869222 @default.
- W3044195506 cites W2169659168 @default.
- W3044195506 cites W2294422333 @default.
- W3044195506 cites W2575120333 @default.
- W3044195506 cites W2623431351 @default.
- W3044195506 cites W2736601468 @default.
- W3044195506 cites W2739657930 @default.
- W3044195506 cites W2766447205 @default.
- W3044195506 cites W2779040504 @default.
- W3044195506 cites W2781726626 @default.
- W3044195506 cites W2785315072 @default.
- W3044195506 cites W2898227854 @default.
- W3044195506 cites W2908261578 @default.
- W3044195506 cites W2911719076 @default.
- W3044195506 cites W2943197047 @default.
- W3044195506 cites W2949899112 @default.
- W3044195506 cites W2963094322 @default.
- W3044195506 cites W2963407617 @default.
- W3044195506 cites W2963934958 @default.
- W3044195506 cites W2964263543 @default.
- W3044195506 cites W2964273112 @default.
- W3044195506 cites W2972758308 @default.
- W3044195506 cites W2974316376 @default.
- W3044195506 cites W2981234930 @default.
- W3044195506 cites W2982316857 @default.
- W3044195506 cites W2986185262 @default.
- W3044195506 cites W2991046523 @default.
- W3044195506 cites W2996477464 @default.
- W3044195506 cites W3002128304 @default.
- W3044195506 cites W3030848229 @default.
- W3044195506 cites W3093287223 @default.
- W3044195506 hasPublicationYear "2020" @default.
- W3044195506 type Work @default.
- W3044195506 sameAs 3044195506 @default.
- W3044195506 citedByCount "0" @default.
- W3044195506 crossrefType "posted-content" @default.
- W3044195506 hasAuthorship W3044195506A5011250157 @default.
- W3044195506 hasAuthorship W3044195506A5039829761 @default.
- W3044195506 hasAuthorship W3044195506A5041433085 @default.
- W3044195506 hasAuthorship W3044195506A5065053322 @default.
- W3044195506 hasConcept C107457646 @default.
- W3044195506 hasConcept C111368507 @default.
- W3044195506 hasConcept C111919701 @default.
- W3044195506 hasConcept C119857082 @default.
- W3044195506 hasConcept C12725497 @default.
- W3044195506 hasConcept C127313418 @default.
- W3044195506 hasConcept C127705205 @default.
- W3044195506 hasConcept C154945302 @default.
- W3044195506 hasConcept C177264268 @default.
- W3044195506 hasConcept C18903297 @default.
- W3044195506 hasConcept C199360897 @default.
- W3044195506 hasConcept C2777212361 @default.
- W3044195506 hasConcept C2780490138 @default.
- W3044195506 hasConcept C2986087404 @default.
- W3044195506 hasConcept C41008148 @default.
- W3044195506 hasConcept C49774154 @default.
- W3044195506 hasConcept C86803240 @default.
- W3044195506 hasConcept C91306197 @default.
- W3044195506 hasConcept C97541855 @default.
- W3044195506 hasConceptScore W3044195506C107457646 @default.
- W3044195506 hasConceptScore W3044195506C111368507 @default.
- W3044195506 hasConceptScore W3044195506C111919701 @default.
- W3044195506 hasConceptScore W3044195506C119857082 @default.
- W3044195506 hasConceptScore W3044195506C12725497 @default.
- W3044195506 hasConceptScore W3044195506C127313418 @default.
- W3044195506 hasConceptScore W3044195506C127705205 @default.
- W3044195506 hasConceptScore W3044195506C154945302 @default.
- W3044195506 hasConceptScore W3044195506C177264268 @default.
- W3044195506 hasConceptScore W3044195506C18903297 @default.
- W3044195506 hasConceptScore W3044195506C199360897 @default.
- W3044195506 hasConceptScore W3044195506C2777212361 @default.
- W3044195506 hasConceptScore W3044195506C2780490138 @default.
- W3044195506 hasConceptScore W3044195506C2986087404 @default.
- W3044195506 hasConceptScore W3044195506C41008148 @default.
- W3044195506 hasConceptScore W3044195506C49774154 @default.
- W3044195506 hasConceptScore W3044195506C86803240 @default.
- W3044195506 hasConceptScore W3044195506C91306197 @default.
- W3044195506 hasConceptScore W3044195506C97541855 @default.
- W3044195506 hasLocation W30441955061 @default.
- W3044195506 hasOpenAccess W3044195506 @default.
- W3044195506 hasPrimaryLocation W30441955061 @default.
- W3044195506 hasRelatedWork W1505810844 @default.