3.4 Methods

์ด๋ฒˆ section์—์„œ๋Š” policy gradient๋ฅผ ์–ด๋–ป๊ฒŒ ์ด MARL ํ™˜๊ฒฝ์— ์ ์šฉ์‹œํ‚ฌ์ง€์— ๋Œ€ํ•œ ์ ‘๊ทผ์„ ์„ค๋ช…ํ•ฉ๋‹ˆ๋‹ค.

Last updated