Zishun Yu

Zishun Yu, Yunzhe Tao, Liyu Chen et al.

Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leveraged the power of reinforcement learning (RL) in conjunction with large language models (LLMs), significantly enhancing code generation capabilities. The application of RL focuses on directly optimizing for functional correctness, offering an advantage over conventional supervised methods. Despite policy-based RL methods dominating the literature on RL for program synthesis, the nature of program synthesis tasks hints at a natural alignment with value-based methods. This stems from the rich collection of off-policy programs, including those developed by human programmers and also historical samples, coupled with the straightforward verification of generated programs through automated unit testing, meaning rewards are easy to obtain. Diverging from the dominant use of policy-based algorithms, our work explores the feasibility of value-based approaches, leading to the development of our $\mathcal{B}$-Coder (pronounced Bellman coder). Yet, training value-based methods presents challenges due to the enormous search space inherent to program synthesis. To this end, we introduce an initialization protocol for RL agents utilizing pre-trained LMs and a conservative Bellman operator to reduce training complexities. Moreover, we demonstrate how to leverage the learned value functions as a dual strategy to post-process generated programs. Our empirical evaluations demonstrated $\mathcal{B}$-Coder's capability in achieving state-of-the-art performance when compared to policy-based methods. Remarkably, this achievement is reached with minimal reward engineering effort, highlighting the effectiveness of value-based RL, independent of reward designs.

Ian A. Kash, Lev Reyzin, Zishun Yu

Reinforcement learning generalizes multi-armed bandit problems with additional difficulties of a longer planning horizon and unknown transition kernel. We explore a black-box reduction from discounted infinite-horizon tabular reinforcement learning to multi-armed bandits, where, specifically, an independent bandit learner is placed in each state. We show that, under ergodicity and fast mixing assumptions, any slowly changing adversarial bandit algorithm achieving optimal regret in the adversarial bandit setting can also attain optimal expected regret in infinite-horizon discounted Markov decision processes, with respect to the number of rounds $T$. Furthermore, we examine our reduction using a specific instance of the exponential-weight algorithm.

Zishun Yu, Tengyu Xu, Di Jin et al.

Solving mathematics problems has been an intriguing capability of large language models, and many efforts have been made to improve reasoning by extending reasoning length, such as through self-correction and extensive long chain-of-thoughts. While promising in problem-solving, advanced long reasoning chain models exhibit an undesired single-modal behavior, where trivial questions require unnecessarily tedious long chains of thought. In this work, we propose a way to allow models to be aware of inference budgets by formulating it as utility maximization with respect to an inference budget constraint, hence naming our algorithm Inference Budget-Constrained Policy Optimization (IBPO). In a nutshell, models fine-tuned through IBPO learn to ``understand'' the difficulty of queries and allocate inference budgets to harder ones. With different inference budgets, our best models are able to have a $4.14$\% and $5.74$\% absolute improvement ($8.08$\% and $11.2$\% relative improvement) on MATH500 using $2.16$x and $4.32$x inference budgets respectively, relative to LLaMA3.1 8B Instruct. These improvements are approximately $2$x those of self-consistency under the same budgets.