# B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

arXiv: https://arxiv.org/abs/2310.03173 · HTML: https://mlsanity.com/paper/2310.03173/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 105 references that are in the map.
- First posted on arXiv 4 Oct 2023.

## Builds on (most cited first, 30 of 76)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)

## Built on by (most cited first, 17 of 17)

- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems](https://mlsanity.com/paper/2505.15201/) (2025)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models](https://mlsanity.com/paper/2506.04210/) (2025)
- [How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark](https://mlsanity.com/paper/2406.06647/) (2024)
- [Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization](https://mlsanity.com/paper/2501.17974/) (2025)
- [MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions](https://mlsanity.com/paper/2410.02743/) (2024)
- [Training Language Models to Generate Quality Code with Program Analysis Feedback](https://mlsanity.com/paper/2505.22704/) (2025)
- [AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction](https://mlsanity.com/paper/2510.15339/) (2025)
- [Re-Aligning Language to Visual Objects with an Agentic Workflow](https://mlsanity.com/paper/2503.23508/) (2025)
- [ShiQ: Bringing back Bellman to LLMs](https://mlsanity.com/paper/2505.11081/) (2025)
- [RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment](https://mlsanity.com/paper/2506.21037/) (2025)
- [NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification](https://mlsanity.com/paper/2508.02823/) (2025)
- [Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs](https://mlsanity.com/paper/2504.15210/) (2025)
- [Language Model Distillation: A Temporal Difference Imitation Learning Perspective](https://mlsanity.com/paper/2505.20335/) (2025)
- [RLPF: Reinforcement Learning from Performance Feedback for Code Generation](https://mlsanity.com/paper/2607.27271/) (2026)
- [Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents](https://mlsanity.com/paper/2610.03634/) (2026)

## Abstract (arXiv)

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 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 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.