https://honglu2875.github.io/tags/reinforcement-learning/ Recent content in Reinforcement Learning on Honglu Fan Hugo en-us Sun, 30 Jun 2024 05:16:55 -0400 https://honglu2875.github.io/posts/2024-06-30-mcts-and-theorem-proving/ Sun, 30 Jun 2024 05:16:55 -0400 https://honglu2875.github.io/posts/2024-06-30-mcts-and-theorem-proving/ <p>With the increasing maturity of the <a href="https://github.com/leanprover/lean4.git">Lean theorem prover</a>, many people have attempted the combination of reinforcement learning (RL) and theorem proving. Among many attempts, the <a href="https://arxiv.org/abs/2205.11491">Hypertree proof search</a> has been quite notable which I admire a lot personally.</p> <p>Looking around, the general field of neural reasoning has also becoming a more prominent field since logical reasoning has been one of a few domains where LLM continues to struggle towards a satisfactory degree of reliability. A nice recent survey is <a href="https://arxiv.org/html/2404.09939v1">this</a>.</p>