[HN Gopher] Offline Reinforcement Learning for LLM Multi-Step Re...
       ___________________________________________________________________
        
       Offline Reinforcement Learning for LLM Multi-Step Reasoning
        
       Author : belter
       Score  : 88 points
       Date   : 2024-12-23 10:16 UTC (12 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | fnqi8ckfek wrote:
       | Gee I can't even understand the abstract.
       | 
       | Can someone explain in plain English how RL is even doable here,
       | let alone desirable?
        
         | elcomet wrote:
         | Multi-step reasoning means that the LLM is giving a question
         | (maths here), and generating an answer that consists of many
         | intermediate words, before returning the solution. Here, we
         | don't want to tell the LLM how to solve the problem word-by-
         | word. We want to tell it at the end, "correct" or "incorrect",
         | and have the model learn on its own to generate intermediate
         | steps, to reach the solution.
         | 
         | That's typically a setup where RL is desirable (even
         | necessary): we have sparse rewards (only at the end) and give
         | no details to the model on how to reach the solution. It's
         | similar to training models to play chess against a specific
         | opponent.
        
           | twometwo wrote:
           | What is a ELI5 explanation of KL-regularization and entropy
           | maximization to select the policy?
           | 
           | Edited: I found this to be useful for explaining maximum
           | entropy https://awjuliani.medium.com/maximum-entropy-
           | policies-in-rei...
           | 
           | I think that in chess you take a piece and that increases the
           | value but you have to consider the position (that is how your
           | pieces can move) and that is the entropy. So maximum entropy
           | is taking pieces but considering strategic position (policy).
           | But there must be a confluence term, that is how well having
           | many players or new states is a good thing to have. Don't
           | know how to math relate that "confluence" term to entropy.
           | From a computer point of view having a huge number of states
           | makes computation of best move impossible but at the same
           | time can make the optimum larger, so it is related to how
           | given the computer power the algorithm can approximate a
           | maximum that is an increasing function of the number of
           | states. There must be a trade off here that I called
           | confluence.
           | 
           | Also thanks for all explanations.
        
             | Alifatisk wrote:
             | About KL-regularization, think of it like training wheels
             | for the robot's brain. It helps the robot's learning
             | process by preventing it from making drastic changes to its
             | strategy too quickly.
             | 
             | It's like saying, "Hey robot, remember what you learned
             | last time? Don't forget it completely, but feel free to
             | adjust a bit."
        
             | porridgeraisin wrote:
             | You will have hyperparameters that weight the KL divergence
             | (between the updated policy distribution and the current
             | policy distribution). This helps you tune how sensitive the
             | training process is. Entropy maximization is common in
             | offline RL specifically as it ensures the policy has some
             | non determinism at least and isn't bound too closely to the
             | data you have collected, to the point of basically being
             | deterministic. This is also tunable with a weight.
        
         | reissbaker wrote:
         | RL works when you have some kind of verifier or ground truth;
         | e.g. for math (and to some extent, coding, if you have tests
         | and/or a type checker). You can also do it for simulations.
         | This paper focuses on math and "embodied agent control" (i.e.
         | simulation).
        
       | theapadayo wrote:
       | Well I guess we finally got the mythical 'Q*'. Or at least some
       | variant of it using energy functions (I think that's what they
       | mean by 'soft' Q-learning?). The extra boost from using the value
       | function at test time is interesting as well.
        
       ___________________________________________________________________
       (page generated 2024-12-23 23:01 UTC)