Deep RL

Recap: Value function approximation

Deep value function approximation

JAX

Deep Q-learning

Deep Q-learning in JAX

General Value Functions

The reward hypothesis (Sutton and Barto 2018)

General value functions (Sutton et al. 2011)

Example: Simple predictive questions

GVFs as Auxiliary Tasks

Trade-offs in multi-task learning

Open problems in GVF learning

Distributional RL

…

• Title:

• Author: wy

• Created at
  : 2023-07-23 18:59:37

•           **Updated at
                :** 2023-07-23 20:24:13
        
    
    
  

•       **Link:** https://yuuee-www.github.io/blog/2023/07/23/RL/step10/RLstep10/
    
    
  

•       **
            License:
        **
        
  
        
            This work is licensed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0).
        
    
  
  
        
    
  
    
  
    
  
    
        
            
                
                    [Prev posts](/2023/07/23/RL/step11/RLstep11/)
                
            
            
                
                    [Next posts](/2023/07/23/RL/step9/RLstep9/)
                
            
        
    
  
    
        
            
  
  
    Comments
  
  
  
    
        
  
  
  
    
  
  
        
    
  
  
  
    
        
  
    On this page
  

1. Deep RL

2. Deep value function approximation

3. General Value Functions

      ©
      
        2022
        -
      
      2024    [wy](/)
      
          
          
   
              
                  24 posts in total
              
              
          
   
      
   
   
      
      
          
              
                  VISITOR COUNT
                  
              
          
          
              
                  TOTAL PAGE VIEWS
                  
              
          
      
   
   
      POWERED BY [Hexo](https://hexo.io)
      THEME [Redefine v2.6.4](https://github.com/EvanNotFound/hexo-theme-redefine)
   
   
   
      
          Blog up for  days  hrs  Min  Sec
   

-

-

-

-

-

-

-