<div id="readability-page-1" class="page"><div>
	
	
	
		
		
		
		
		
		
	

	
	
	

	

	
	<div id="viewTypeSelector" data-docversion="1.0">



<div>
         
<div><p><a href="/PostList.naver?blogId=dnddnjs11&amp;categoryNo=9&amp;logCode=0&amp;categoryName=RLCode" onclick="nclk(this, 'pst.board', '', '');">RLCode</a></p></div>

        
     	
        <div>
	                <p>
                        <h3>
                            Tetris 학습시키기
                            
                        </h3>
	                </p>
	            </div>
        
        
        
<div>

	<p><a href="/PostList.naver?blogId=dnddnjs11" onclick="nclk(this, 'pst.writer', '', '');">

		<span><img src="https://blogpfthumb-phinf.pstatic.net/MjAxNjExMDFfMTAx/MDAxNDc3OTYyNjk4NzEx.Ofz5a9exbyN37s7TFVVafvIc9yWcqjvh8tzy1jJkbT4g.bHezESnf7Xk7LSGwKtyJzfxx0vqTkQ2LwDRf_hpwZEAg.JPEG.dnddnjs11/profileImage.jpg?type=s1" width="35" height="35" alt="프로필"></span>
	</a></p><div>
		<p><a href="/PostList.naver?blogId=dnddnjs11" onclick="nclk(this, 'pst.writer', '', '');"><strong>이웅원</strong></a>
	</p></div>
	<p>2016. 11. 3. 2:25
	</p>
</div>

<div>
		<p><a href="#" isblackuser="false" onclick="nclk(this, 'pst.add', '', '');"><span></span> 이웃추가</a></p>

</div>



        
        
        
    </div>







<div>
    



















    











<div>
                    <p>
                        <h6>1. 목적</h6>
                    </p>
                </div>







    








<div>
                    <p><span>유명하고 간단한 그러나 학습하기에는 쉽지 않은 Tetris를 학습시켜 봄으로서 강화학습 알고리즘의 적용과 구현에 대한 능력을 키운다<br></span><span><br></span></p>
                </div>










    











<div>
                    <p>
                        <h6>2. 코드</h6>
                    </p>
                </div>







    








<div>
                        <p><a target="_blank" href="https://github.com/ReinforcementLearning/Tetris">https://github.com/ReinforcementLearning/Tetris</a></p>
                    </div>










    







<div id="SEDOC-1478107519765-1675653620_oglink_0">
                
                <a href="https://github.com/ReinforcementLearning/Tetris" target="_blank">
                    <p><img src="https://dthumb-phinf.pstatic.net/?src=%22https%3A%2F%2Favatars0.githubusercontent.com%2Fu%2F22538228%3Fv%3D3%26s%3D400%22&amp;type=ff120" alt="">
					</p>
                    <div>
                        <p>ReinforcementLearning/Tetris</p>
                        <p>Reinforcement Leanring for Tetris</p>
                        <p>github.com</p>
                    </div>
                
                </a>
                    
            </div>












    











<div>
                    <p>
                        <h6><br>3. 참고자료</h6>
                    </p>
                </div>







    








<div>
                        <p><span><a target="_blank" href="http://cs231n.stanford.edu/reports2016/121_Report.pdf">http://cs231n.stanford.edu/reports2016/121_Report.pdf</a><br></span><span></span></p>
                    </div>










    







<div id="SEDOC-1478107519765-1675653620_oglink_1">
                
                <a href="http://cs231n.stanford.edu/reports2016/121_Report.pdf" target="_blank">
                    <div>
                        <p>cs231n.stanford.edu</p>
                    </div>
                
                </a>
                    
            </div>












    








<div>
                        <p><a target="_blank" href="http://melax.github.io/tetris/tetris.html">http://melax.github.io/tetris/tetris.html</a></p>
                    </div>










    







<div id="SEDOC-1478107519765-1675653620_oglink_2">
                
                <a href="http://melax.github.io/tetris/tetris.html" target="_blank">
                    <p><img src="https://dthumb-phinf.pstatic.net/?src=%22http%3A%2F%2Fmelax.github.io%2Ftetris%2Ftetris_pieces.gif%22&amp;type=ff120" alt="">
					</p>
                    <div>
                        <p>Reinforcement Learning Tetris Example</p>
                        <p>melax.github.io</p>
                    </div>
                
                </a>
                    
            </div>












    



















</div>



</div>

	
	
	
	
	
	
		
	
	
	

	
	
  <div>
        
          <p><a href="/CommentList.naver?blogId=dnddnjs11&amp;logNo=220852142159" onclick="nclk(this, 'pst.re', '', '');">
            <span>댓글</span> <em>0</em>
          </a>
        
        
      </p></div>

  
  
  <div>
      <a href="/dnddnjs11" onclick="nclk(this, 'pst.pfwriter', '', '');">
        <p><span><img src="https://blogpfthumb-phinf.pstatic.net/MjAxNjExMDFfMTAx/MDAxNDc3OTYyNjk4NzEx.Ofz5a9exbyN37s7TFVVafvIc9yWcqjvh8tzy1jJkbT4g.bHezESnf7Xk7LSGwKtyJzfxx0vqTkQ2LwDRf_hpwZEAg.JPEG.dnddnjs11/profileImage.jpg?type=s1" width="48" height="48" alt="이웅원"></span>
          
          
        </p>
        <div>
          
          <p><strong>이웅원</strong></p><p>인공지능, 드론, 로봇

인공지능을 옳은 방향으로 이끄는 엔지니어</p>
        </div>
      </a>
      <div>
        
          
          
          
          
            <p><span><a href="#" isblackuser="false" onclick="nclk(this, 'pst.pfaddn', '', '');"><span></span>이웃추가</a></span>
          
        
        
        
      </p></div>
      
      
    </div>
  

  
  
  

  
  

  
  
  
  
  
  
  
</div></div>

Reinforce Yourself

1. 목적유명하고 간단한 그러나 학습하기에는 쉽지 않은 Tetris를 학습시켜 봄으로서 강화학습 알고리즘의 적용과 구현에 대한 능력을 키운다 2. 코드https://github.com/ReinforcementLearning/Tetris 3. 참고자료http://cs231n.stanford.edu/reports2016/121_Report.pdf http://melax.github.io/tetris/tetris.html