๐œ€-greedy

Q-Learning

Reinforcement Learning, Q-Learning

๊ฐ•ํ™” ํ•™์Šต(Reinforcement Learning)์—์„œ ์‚ฌ์šฉํ•˜๋Š” Q-Learning์— ๋Œ€ํ•ด์„œ ์•Œ์•„ ๋ณด๊ณ  Gym์—์„œ ์ œ๊ณตํ•˜๋Š” ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๊ธฐ ์œ„ํ•œ ์•Œ๊ณ ๋ฆฌ๋“ฌ์„ ๋งŒ๋“ค์–ด ๋ณด์ž.

SARSA Learning

Reinforcement Learning, Temporal-Difference Learning

๊ฐ•ํ™” ํ•™์Šต(Reinforcement Learning)์—์„œ ์‚ฌ์šฉํ•˜๋Š” SARSA์— ๋Œ€ํ•ด์„œ ์•Œ์•„ ๋ณด๊ณ  Gym์—์„œ ์ œ๊ณตํ•˜๋Š” ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๊ธฐ ์œ„ํ•œ ์•Œ๊ณ ๋ฆฌ๋“ฌ์„ ๋งŒ๋“ค์–ด ๋ณด์ž.