A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions

• URL: http://arxiv.org/abs/2606.16733v1
• Date: Mon, 15 Jun 2026 13:55:23 GMT
• Title: A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions
• Abstract summary: Policy gradient algorithms for language models optimize the same objective $J() = mathbbE*sim p*()[R()]$.<n>Every method from REINFORCE to PPO to GRPO modifies one or both factors to address a specific failure in the preceding formulation.<n>This survey revisits the landscape of LLM policy optimization from $J()$ on first principles.
• Score: 22.979195282807144
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policy gradient algorithms for language models optimize the same objective $J(θ) = \mathbb{E}*{τ\sim p*θ(τ)}[R(τ)]$, which has exactly two factors: the trajectory probability $p_θ(τ)$ and the reward $R(τ)$. Every method from REINFORCE to PPO to GRPO and their descendants modifies one or both factors to address a specific failure in the preceding formulation. Existing surveys organize these methods by domain or chronology, which obscures the rationale behind each design choice and the precise location of its intervention within the gradient estimator. This survey revisits the landscape of LLM policy optimization from $J(θ)$ on first principles and uses the trajectory side, induced by $p_θ(τ)$, and the reward side, induced by $R(τ)$, as the two axes along which methods are located. It covers the path from REINFORCE and PPO to GRPO, as well as post-GRPO variants, Agentic RL, and GRPO-OPD. The resulting framework is unified, diagnostic, and extensible: it analyzes methods from a shared objective, identifies which side each method modifies and why, and applies the same trajectory and reward axes across these settings. Across these settings, the framework also exposes compound failures that no single-side fix resolves and that therefore require joint design of the trajectory side and the reward side. The boundary cases and coupled failures identified by this map mark where existing solutions run out and provide a principled starting point for designing the next generation of LLM policy optimization algorithms.

Related papers

• Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex [43.502315311491635]
  Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity.<n>This work reveals that these optimization strategies share a common geometric structure: each implicitly defines a target distribution on the response simplex and projects toward it via first-order approximation.<n>We propose Listwise Policy Optimization (LPO) to explicitly conduct the target-projection, which demystifies the implicit target by restricting the proximal RL objective to the response simplex, and then projects the policy via exact divergence minimization.
  arXiv  Detail & Related papers  (2026-05-07T12:38:17Z)
• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning [17.245293915129942]
  The optimal objective is a fundamental aspect of reinforcement learning (RL)<n>While total return is ideal, discounted return is practical objective due to its stability.<n>We propose two alternative approaches to align the objectives.
  arXiv  Detail & Related papers  (2024-07-18T08:33:10Z)
• Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning [62.81324245896717]
  We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-ite convergence guarantees under (weak) gradient domination assumptions. We numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-07-15T14:54:57Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Scalable Online Exploration via Coverability [45.66375686120087]
  Exploration is a major challenge in reinforcement learning, especially for high-dimensional domains that require function approximation. We introduce a new objective, $L_Coverage, which generalizes previous exploration schemes and supports three fundamental desideratas. $L_Coverage enables the first computationally efficient model-based and model-free algorithms for online (reward-free or reward-driven) reinforcement learning in MDPs with low coverability.
  arXiv  Detail & Related papers  (2024-03-11T10:14:06Z)
• Surpassing legacy approaches to PWR core reload optimization with single-objective Reinforcement learning [0.0]
  We have developed methods based on Deep Reinforcement Learning (DRL) for both single- and multi-objective optimization. In this paper, we demonstrate the advantage of our RL-based approach, specifically using Proximal Policy Optimization (PPO) PPO adapts its search capability via a policy with learnable weights, allowing it to function as both a global and local search method.
  arXiv  Detail & Related papers  (2024-02-16T19:35:58Z)
• PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback [106.63518036538163]
  We present a novel unified bilevel optimization-based framework, textsfPARL, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning. Our framework addressed these concerns by explicitly parameterizing the distribution of the upper alignment objective (reward design) by the lower optimal variable. Our empirical results substantiate that the proposed textsfPARL can address the alignment concerns in RL by showing significant improvements.
  arXiv  Detail & Related papers  (2023-08-03T18:03:44Z)
• Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning [17.916366827429034]
  We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions. We propose an Anchor-changing Regularized Natural Policy Gradient framework, which can incorporate ideas from well-performing first-order methods.
  arXiv  Detail & Related papers  (2022-06-10T21:09:44Z)
• Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm [50.50545326342971]
  We formulate the problem of maximizing a non-linear concave function of multiple long-term objectives.<n>A policy-gradient based model-free algorithm is proposed for the problem.<n>The proposed algorithm is shown to achieve convergence to within an $epsilon$ of the global optima.
  arXiv  Detail & Related papers  (2021-05-28T22:20:54Z)
• Provably Efficient Exploration in Policy Optimization [117.09887790160406]
  This paper proposes an Optimistic variant of the Proximal Policy Optimization algorithm (OPPO) OPPO achieves $tildeO(sqrtd2 H3 T )$ regret. To the best of our knowledge, OPPO is the first provably efficient policy optimization algorithm that explores.
  arXiv  Detail & Related papers  (2019-12-12T08:40:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.