• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) °ÔÀÓ°ú ·Îº¿°øÇп¡¼­ÀÇ ¸ðµ¨ ÇÁ¸® °­È­ÇнÀ ÀÀ¿ë¿¡ ´ëÇÑ »ç·Ê Á¶»ç
¿µ¹®Á¦¸ñ(English Title) Case Studies on Model-Free Control Applications for Games and Robotics
ÀúÀÚ(Author) ±è¼¼¿ø   ÀÌÀç±æ   Sewon Kim   Jae-Gil Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 35 NO. 02 PP. 0126 ~ 0138 (2019. 08)
Çѱ۳»¿ë
(Korean Abstract)
°­È­ÇнÀÀº ¿¡ÀÌÀüÆ®°¡ ȯ°æÀ¸·ÎºÎÅÍ ÇöÀçÀÇ »óŸ¦ ÀÎÁöÇÏ°í ¼öÇàÇÑ Çൿ¿¡ ´ëÇÑ Çǵå¹éÀ» ¹ÞÀ¸¸ç ÇнÀÀ» ÁøÇàÇÑ´Ù. °­È­ÇнÀÀº ¿©·¯ ÀÀ¿ë¿¡¼­ È°¹ßÈ÷ ¿¬±¸µÇ°í ÀÖÁö¸¸, ƯÈ÷ °ÔÀÓ°ú ·Îº¿¿¡ ´ëÇÑ ¹®Á¦´Â ¸¶¸£ÄÚÇÁ °áÁ¤ °úÁ¤À¸·Î ½±°Ô Ç¥ÇöÇÒ ¼ö ÀÖ¾î °­È­ÇнÀÀ» Àû¿ëÇϱ⿡ ¿ëÀÌÇÏ´Ù. ¸ðµ¨ ÇÁ¸® °­È­ÇнÀÀÇ Á¾·ù´Â ¸óÅ×, Ä«¸¦·Î ÄÁÆ®·Ñ, »ì»ç, Å¥·¯´×, Á¤Ã¥ °æ»ç ¹æ¹ý µîÀÌ ÀÖÀ¸¸ç ¹®Á¦ »óȲ¿¡ µû¶ó ¾Ë¸ÂÀº ¹æ¹ýÀ» »ç¿ëÇÑ´Ù. °ÔÀÓ°ú ·Îº¿°ú °ü·ÃÇÑ ¹®Á¦¸¦ Ç®±â À§ÇØ ¸ðµ¨ ÇÁ¸® °­È­ÇнÀ ¾Ë°í¸®ÁòÀÌ ÁÖ·Î »ç¿ëµÇ¸ç µö Å¥·¯´×°ú Á¤Ã¥ °æ»ç ¹æ¹ýÀÌ ´ëÇ¥ÀûÀ¸·Î »ç¿ëµÇ¾î¿Ô´Ù. ÇÏÁö¸¸ ÁÖ¾îÁø ȯ°æ¿¡ ´ëÇÑ Á¤º¸°¡ ÃæºÐÇÏÁö ¾Ê¾Æ¼­ º¸»ó°ú °ü·ÃµÈ Á¤º¸°¡ ÃæºÐÇÏÁö ¾Ê°í, º¸»óÀÌ Áö¿¬µÇ´Â °æ¿ì¿¡´Â °­È­ÇнÀÀÌ Á¦´ë·Î ÀÛµ¿Çϱ⠾î·Á¿î ¹®Á¦°¡ ÀÖ´Ù. ÇâÈÄ ¿¬±¸¿¡¼­´Â ÀÌ·¯ÇÑ ´ÜÁ¡À» º¸¿ÏÇÏ¿©¾ß ÇÒ °ÍÀÌ´Ù ¶ÇÇÑ À̹ø ¿¬±¸¿¡¼­ ´Ù·çÁö ¸øÇÑ °ÔÀÓ°ú ·Îº¿¿¡ °ü·ÃµÈ State-of-the-art ¸¦ ÇâÈÄ ¿¬±¸¿¡¼­ ´Ù·ê °ÍÀÌ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Reinforcement learning is the learning process to enable an agent to understand the current environment and get feedback from the action. Though reinforcement learning has been actively studied in various principles, games and robotics are known to be especially well-suited to a Markov decision process, making them easier to apply reinforcement learning. The types of model-free reinforcement learning include Monte-Carlo control, SARSA, Q-learning, and policy gradient and use the appropriate methods depending on the problem situation. Model-free reinforcement learning algorithms such as deep Q-learning and policy gradient are mainly used to solve the problems related to games and robotics. However, reinforcement learning does not work well in some environments where the reward is delayed or has only insufficient information. We believe that future studies need to address these limitations. We plan to investigate the state-of-the-art of reinforcement learning on game and robotics.
Å°¿öµå(Keyword) Reinforcement learning   Game   Robot   Q-learning   Policy gradient   °­È­ÇнÀ   °ÔÀÓ   ·Îº¿   Å¥·¯´× Á¤Ã¥ °æ»ç  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå