ºÇ½ª¹¹¿·¡§ orika_ex_miyako 2023ǯ09·î08Æü(¶â) 12:20:32ÍúÎò
¡¡²¼µ¤Î Unity ¸ø¼°Github ¤«¤é¥¤¥ó¥¹¥È¡¼¥ë¤·¤Þ¤¹¡£
Unity-Technologies/ml-agents
https://github.com/Unity-Technologies/ml-agents
¡¡³Ø½¬¤ò³«»Ï¤¹¤ë¾ì¹ç¡¢¤Þ¤º¤Ï Anaconda Prompt ¤Ë¤Æ¥³¥Þ¥ó¥É¤ò¼Â¹Ô¤·¤Þ¤¹¡£
yaml¥Õ¥¡¥¤¥ë¤òºîÀ®¤·¤¿¥Õ¥©¥ë¥À¤Þ¤Ç³¬Áؤò°ÜÆ°¤·¤¹¤ëɬÍפ¬¤¢¤ê¤Þ¤¹¤Î¤Ç¡¢
º£²ó¤Ç¤¢¤ì¤Ð¡¢config/ppo ¥Õ¥©¥ë¥À¤ò»ØÄꤷ¡¢Â³¤±¤Æ¡¢°Ê²¼¤Î¤è¤¦¤ËÆþÎϤ·¤Þ¤¹¡£
mlagents-learn ./trainer_config.yaml --run-id testId
¡¡³Ø½¬¤Î½àÈ÷¤¬À°¤¦¤È¡¢²¼µ¤Î¤è¤¦¤Ê Unity ¤Î¥í¥´¤¬É½¼¨¤µ¤ì¤Þ¤¹¡£
¡¡¤½¤Î¸å¡¢Unity ¥¨¥Ç¥£¥¿¡¼¤ÎºÆÀ¸(Play)¥Ü¥¿¥ó¤ò²¡¤¹¤È¡¢³Ø½¬¤¬¥¹¥¿¡¼¥È¤·¤Þ¤¹¡£
¡¡³Ø½¬Ãæ¤Ï¡¢¤º¤Ã¤È Anaconda Prompt Æâ¤Ç¥í¥°¤¬Î®¤ì¤Þ¤¹¡£
¡¡¥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
»²¹Í¥µ¥¤¥È
¤«¤á¤¯¤áÍÍ
Unity¤ÇML-Agents¤ò»È¤Ã¤¿µ¡³£³Ø½¬¤Î´Ä¶ºî¤ê¤ò¤¹¤ë
- ¥«¥Æ¥´¥ê¡§
- ¿Ê³Ø/¥¹¥¯¡¼¥ë
- ¥×¥í¥°¥é¥ß¥ó¥°
¥³¥á¥ó¥È¤ò¤«¤¯