예제 소스테트리스를 배우는 강화학습 에이전트 만들기 · 파일 31개CLAUDE.md3.2 KBllm_macro_client.py32.8 KBllm_reward_wrapper.py3.2 KBllm_teacher.py4.3 KBmoe_macro_policy.py2.7 KBproject.md2.1 KBqt_rl_client.py5.4 KBrequirements.txt128 Btrain_qt_live.py27.7 KBtrain_tetris_rl.py11.3 KBvlm_macro_client.py7.8 KBvlm_teacher.py6.1 KBconfig__init__.py55 Brl_config.py3.2 KBllms/Qwen2.5-VL-3B-Instructchat_template.json1.0 KBconfig.json1.3 KBgeneration_config.json218 BLICENSE7.2 KBmodel.safetensors.index.json63.9 KBpreprocessor_config.json350 BREADME.md17.8 KBtokenizer_config.json5.6 KBtetrisCMakeLists.txt1.9 KBtetris/srcmain_window.cpp12.8 KBmain_window.h1.4 KBmain.cpp1.1 KBtetris_c_api.cpp6.4 KBtetris_engine.cpp13.0 KBtetris_engine.h4.3 KBtetris_widget.cpp3.4 KBtetris_widget.h536 B__init__.pyfrom .rl_config import CONFIG, RLConfig # noqa: F401