| ²é¿´: 694 | »Ø¸´: 1 | ||
ww108809гæ (³õÈëÎÄ̳)
|
[ÇóÖú]
ÇóÒ»¶ÎÓÃJavaʵÏֵIJéÕÒ±íʵÏÖRL(Ç¿»¯Ñ§Ï°)µÄ´úÂë(ĿǰûÓнð±Ò£¬ÓÐÐèÒª¿ÉÒÔ³äÖµ....)
|
|
3) Describe your application of RL (Q-learning) to Robocode. a) Describe in your own words the Q-learning algorithm. ÎÒÕâÀïÓÐÒ»¶Î´úÂ룬ÐèÒªÁíÒ»¸öʵÏֵķ½·¨£¬ÓÉÓÚ±¾È˶ÔÈ˹¤ÖÇÄÜ·½Ã治̫Á˽⣬ËùÒÔÏëÇë´ó¼Ò°ï°ïæ¡£ Óг¥¡£¡£¡£°ï±ðÈËд×÷Òµ£¬¸ãµ½×Ô¼º²»»áŪÁË£¬Ì«²ÒÁË¡£¡£ ![]() |
» ²ÂÄãϲ»¶
»¯Ñ§µ÷¼ÁÇóÖú
ÒѾÓÐ14È˻ظ´
²ÄÁÏÀà284µ÷¼Á
ÒѾÓÐ12È˻ظ´
²ÄÁÏ¿¼ÑÐÇóµ÷¼Á×Ü·Ö280
ÒѾÓÐ31È˻ظ´
325·Ö»¯Ñ§µ÷¼Á
ÒѾÓÐ9È˻ظ´
Óб¬ÁÏ£¬Ò»¸öÇàÄê½ÌʦÂô·¿µÃ400Íò£¬È»ºó»»ÁËÒ»¸öËÄÇàñ×Ó
ÒѾÓÐ4È˻ظ´
Ò»Ö¾Ô¸211£¬0703»¯Ñ§305·ÖÇóµ÷¼Á
ÒѾÓÐ21È˻ظ´
0703»¯Ñ§µ÷¼Á 348·Ö
ÒѾÓÐ15È˻ظ´
0703»¯Ñ§Çóµ÷¼Á
ÒѾÓÐ6È˻ظ´
368»¯Ñ§Çóµ÷¼Á
ÒѾÓÐ7È˻ظ´
±¾¿Æ211£¬293·ÖÇëÇóµ÷¼Á
ÒѾÓÐ12È˻ظ´
ww108809
гæ (³õÈëÎÄ̳)
- Ó¦Öú: 0 (Ó×¶ùÔ°)
- ½ð±Ò: 4.5
- Ìû×Ó: 2
- ÔÚÏß: 21·ÖÖÓ
- ³æºÅ: 2699810
- ×¢²á: 2013-10-05
- רҵ: ÐÅÏ¢×ÊÔ´¹ÜÀí
2Â¥2013-10-18 22:51:19















»Ø¸´´ËÂ¥