Unity¤Ë´ØÏ¢¤¹¤ëµ­»ö¤Ç¤¹

̤

¤«¤á¤¯¤áÍÍ
Unity¤ÇML-Agents¤ò»È¤Ã¤¿µ¡³£³Ø½¬¤Î´Ä¶­ºî¤ê¤ò¤¹¤ë




Python ¦

Annaconda ¥¤¥ó¥¹¥È¡¼¥ë




Python ´Ä¶­¤ÎºîÀ®




Python ¥Ñ¥Ã¥±¡¼¥¸¤Î¥¤¥ó¥¹¥È¡¼¥ë




Py Touch ¥¤¥ó¥¹¥È¡¼¥ë




ML-Agents ¥¤¥ó¥¹¥È¡¼¥ë

Unity ¦

PackageManager ¤«¤é ML-Agents ¥¤¥ó¥¹¥È¡¼¥ë






ÀßÄê


¡¡¥³¥ó¥Ý¡¼¥Í¥ó¥È¤È¥Õ¥¡¥¤¥ë¤ÎÀ°¹çÀ­

yaml ¥Õ¥¡¥¤¥ë
behaviors:
  3DBall:¡¡¡¡¡¡¡¡¡¡//¡¡<=¡¡¤³¤Á¤é¤Î̾Á°¤È Behavior ¤¬°ìÃפ·¤Æ¤¤¤Ê¤¤¤È¡¢¥²¡¼¥àµ¯Æ°»þ¤ËPython¤Ç¥¨¥é¡¼¤¬È¯À¸¤·¤ÆÄä»ß¤¹¤ë
    trainer_type: ppo
    hyperparameters:
      batch_size: 10
      buffer_size: 100
      learning_rate: 0.0003
      beta: 0.005
      epsilon: 0.2
      lambd: 0.99
      num_epoch: 3
      learning_rate_schedule: linear
    network_settings:
      normalize: true
      hidden_units: 128
      num_layers: 2
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.99
        strength: 1.0
    keep_checkpoints: 5
    checkpoint_interval: 500000
    max_steps: 500000
    time_horizon: 64
    summary_freq: 1000
    threaded: true

¥³¥á¥ó¥È¤ò¤«¤¯


¡Öhttp://¡×¤ò´Þ¤àÅê¹Æ¤Ï¶Ø»ß¤µ¤ì¤Æ¤¤¤Þ¤¹¡£

ÍøÍѵ¬Ìó¤ò¤´³Îǧ¤Î¤¦¤¨¤´µ­Æþ²¼¤µ¤¤

Menu



¥×¥í¥°¥é¥à¤Î´ðÁóؽ¬

¥³¡¼¥ÉÎý½¬

µ»½Ñ/Ãμ±(¼ÂÁõÎã)

3D¥¢¥¯¥·¥ç¥ó¥²¡¼¥à

2D¤ª¤Ï¤¸¤­¥²¡¼¥à(ȯŸÊÔ)

2D¶¯À©²£¥¹¥¯¥í¡¼¥ë¥¢¥¯¥·¥ç¥ó(ȯŸÊÔ)

3D¥À¥¤¥Ó¥ó¥°¥¢¥¯¥·¥ç¥ó(ȯŸÊÔ)

2D¥¿¥Ã¥×¥·¥å¡¼¥Æ¥£¥ó¥°(³ÈÄ¥ÊÔ)

¥ì¡¼¥¹¥²¡¼¥à(È´¿è)

2DÊüÃÖ¥²¡¼¥à(ȯŸÊÔ)

3Dæ½Ð¥²¡¼¥à(È´¿è)

2D¥ê¥¢¥ë¥¿¥¤¥à¥¹¥È¥é¥Æ¥¸¡¼

3D¥¿¥Ã¥×¥¢¥¯¥·¥ç¥ó(NavMeshAgent »ÈÍÑ)

2D¥È¥Ã¥×¥Ó¥å¡¼¥¢¥¯¥·¥ç¥ó(¥«¥¨¥ë¤Î°Ù¤Ë¡Á¡¢¥Ü¥³¥¹¥«¥¦¥©¡¼¥ºÉ÷)

3D¥È¥Ã¥×¥Ó¥å¡¼¥¢¥¯¥·¥ç¥ó(ÇòÇ­É÷)

VideoPlayer ¥¤¥Ù¥ó¥ÈϢư¤Î¼ÂÁõÎã

VideoPlayer ¥ê¥¹¥ÈÆâ¤«¤é¥à¡¼¥Ó¡¼ºÆÀ¸¤Î¼ÂÁõÎã(ȯŸ)

AR ²èÁüÉÕ¤­¥ª¥Ö¥¸¥§¥¯¥ÈÀ¸À®¤Î¼ÂÁõÎã

AR ¥ê¥¹¥ÈÆâ¤«¤éÀ¸À®¤Î¼ÂÁõÎã(ȯŸ)

private



¤³¤Î¥µ¥¤¥ÈÆâ¤ÎºîÉʤϥæ¥Ë¥Æ¥£¤Á¤ã¤ó¥é¥¤¥»¥ó¥¹¾ò¹à¤Î¸µ¤ËÄ󶡤µ¤ì¤Æ¤¤¤Þ¤¹¡£

´ÉÍý¿Í/Éû´ÉÍý¿Í¤Î¤ßÊÔ½¸¤Ç¤­¤Þ¤¹