Sign In

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards

์ž‘์„ฑ์ž
  • Haebom
์นดํ…Œ๊ณ ๋ฆฌ
Empty

์ €์ž

Zhixin Han, Yanzhi Zhang, Chuyang Wei, Maohang Gao, Xiawei Yue, Kefei Chen, Yu Zhuang, Haoxiang Guan, Jiyan He, Jian Li, Yitong Duan, Yu Shi, Mengting Hu, Shuxin Zheng

๐Ÿ’ก ๊ฐœ์š”

๋ณธ ์—ฐ๊ตฌ๋Š” ์‹ค์ œ ์„ธ๊ณ„ ์‚ฌ๊ฑด์˜ ๋ฏธ๋ž˜๋ฅผ ์˜ˆ์ธกํ•˜๋Š” '์‹ค์‹œ๊ฐ„ ๋ฏธ๋ž˜ ์˜ˆ์ธก' ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๊ธฐ ์œ„ํ•œ ์ƒˆ๋กœ์šด ๊ฐ•ํ™”ํ•™์Šต ํ™˜๊ฒฝ์ธ FutureWorld๋ฅผ ์ œ์•ˆํ•ฉ๋‹ˆ๋‹ค. FutureWorld๋Š” ์˜ˆ์ธก ์‹œ์ ๋ถ€ํ„ฐ ์‹ค์ œ ๊ฒฐ๊ณผ ํ™•์ธ ๋ฐ ๋ชจ๋ธ ์—…๋ฐ์ดํŠธ๊นŒ์ง€์˜ ํ•™์Šต ๊ณผ์ •์„ ์—ฐ๊ฒฐํ•˜๋ฉฐ, ์ง€์—ฐ๋œ ์‹ค์ œ ๊ฒฐ๊ณผ ๋ณด์ƒ์„ ํ™œ์šฉํ•˜์—ฌ ์—์ด์ „ํŠธ์˜ ์˜ˆ์ธก ์ •ํ™•๋„, ํ™•๋ฅ  ์ ์ˆ˜, ๋ณด์ • ์„ฑ๋Šฅ์„ ํ–ฅ์ƒ์‹œํ‚ต๋‹ˆ๋‹ค.

๐Ÿ”‘ ์‹œ์‚ฌ์  ๋ฐ ํ•œ๊ณ„

โ€ข
์‹ค์ œ ์„ธ๊ณ„์˜ ์ง€์—ฐ๋œ ๊ฒฐ๊ณผ๋ฅผ ๊ฐ•ํ™”ํ•™์Šต ์‹ ํ˜ธ๋กœ ํšจ๊ณผ์ ์œผ๋กœ ํ™œ์šฉํ•  ์ˆ˜ ์žˆ์Œ์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.
โ€ข
์—์ด์ „ํŠธ๊ฐ€ ์‹ค์ œ ์„ธ๊ณ„ ์‚ฌ๊ฑด์„ ๊ธฐ๋ฐ˜์œผ๋กœ ์ง€์†์ ์œผ๋กœ ํ•™์Šตํ•  ์ˆ˜ ์žˆ๋Š” ํ™˜๊ฒฝ์„ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค.
โ€ข
ํ˜„์žฌ๋Š” ์„ธ ๊ฐ€์ง€ ์˜คํ”ˆ์†Œ์Šค ์—์ด์ „ํŠธ์— ๋Œ€ํ•œ ์‹คํ—˜ ๊ฒฐ๊ณผ๋งŒ์„ ์ œ์‹œํ•˜๊ณ  ์žˆ์–ด, ๋‹ค์–‘ํ•œ ์—์ด์ „ํŠธ ๋ฐ ์‹ค์ œ ์ ์šฉ ์‹œ๋‚˜๋ฆฌ์˜ค์— ๋Œ€ํ•œ ์ถ”๊ฐ€์ ์ธ ์—ฐ๊ตฌ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
๐Ÿ‘
Made with Slashpage