Reinforcement Learning : Monte Carlo Method
Baijayanta Roy

Reinforcement Learning : Monte Carlo Method

Baijayanta Roy Baijayanta Roy

Baijayanta Roy

AI/ML| GenAI| Payments |Credit Cards | Digital Banking | |Technology Leader | Cloud Computing | Quantum Computing |API | Tokenization| Product Management | Technology Architecture and Solution

发布日期: 2018年12月7日
+ 关注 
key characteristics of Monte Carlo (MC) method:

There is no model (agent does not know state MDP transitions)
agent learn from sampled experience
learn state value v(s) under policy π by experiencing average return from all sampled episodes (value = average return)
only after a complete episode, values are updated (because of this algorithm convergence is slow and update happens after a episode is Complete)
There is no bootstrapping
Only can be used in episodic problems

 
   
  
 
  

 


                      
  
    

  
            
    
    

    

      
    

      

        
    
    
    

    


      
        
    

  
      

      

    
    
    
    
    
    

    

        要查看或添加评论，请登录
    

  
  
               
    

    
    


          
            

              Baijayanta Roy的更多文章
            

         
        

      

        
          
    
    
    
    

    
    
    

      
  
  
        
      

    

  
  
          
      
        

      

      

        
        
              
    
      


            

              其他会员也浏览了