Multi-Objective Reward and Preference Optimization: Theory and Algorithms

• URL: http://arxiv.org/abs/2512.10601v1
• Date: Thu, 11 Dec 2025 12:51:21 GMT
• Title: Multi-Objective Reward and Preference Optimization: Theory and Algorithms
• Authors: Akhil Agnihotri,
• Abstract summary: This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models.<n>ACPO, e-COP, warmPref-PS, PSPL, and MOPO advance RL across average-cost, episodic, and preference-driven paradigms.<n> Collectively, the thesis unifies RL across average-cost, episodic, and preference-driven paradigms, delivering theoretical advances and practical tools for safe and aligned decision-making.
• Score: 3.316593788543852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Markov Decision Processes (CMDPs) under the average-cost criterion through the Average-Constrained Policy Optimization (ACPO) algorithm. ACPO integrates sensitivity analysis with trust-region updates to ensure stable constraint handling, achieving state-of-the-art empirical performance with theoretical guarantees. Constrained RL is then extended to finite-horizon settings via e-COP, the first policy optimization method for episodic CMDPs. Built on an episodic policy difference lemma, e-COP offers provable performance, simplicity, and scalability in safety-critical environments. The thesis then investigates reinforcement learning from human preferences. warmPref-PS introduces a posterior sampling strategy for linear bandits that integrates offline preference data from heterogeneous raters into online learning. Explicit modeling of rater competence yields substantial regret reduction and more efficient data collection for RLHF. The PSPL algorithm further advances preference-based RL by jointly sampling reward models and transition dynamics from pairwise trajectory comparisons, providing Bayesian simple-regret guarantees and robust empirical identification of optimal policies. The final contribution applies these methods to large-scale model alignment. A multi-objective constrained optimization view yields MOPO, an iterative algorithm with closed-form updates that scales to multi-billion-parameter language models and remains robust across alignment settings. Collectively, the thesis unifies constrained RL across average-cost, episodic, and preference-driven paradigms, delivering theoretical advances and practical tools for safe and aligned decision-making.

Related papers

• Stabilizing Policy Optimization via Logits Convexity [59.242732612484474]
  We show that the convexity of the supervised fine-tuning loss with respect to model logits plays a key role in enabling stable training.<n>Motivated by this observation, we propose Logits Convex Optimization (LCO), a simple yet effective policy optimization framework.
  arXiv  Detail & Related papers  (2026-03-01T07:40:12Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• Policy Regularized Distributionally Robust Markov Decision Processes with Linear Function Approximation [10.35045003737115]
  Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ.<n>We propose DR-RPO, a model-free online policy optimization method that learns robust policies with sublinear regret.<n>We show that DR-RPO can achieve suboptimality bounds and sample efficiency in robust RL, matching the performance of value-based approaches.
  arXiv  Detail & Related papers  (2025-10-16T02:56:58Z)
• Intersection of Reinforcement Learning and Bayesian Optimization for Intelligent Control of Industrial Processes: A Safe MPC-based DPG using Multi-Objective BO [0.0]
  Model Predictive Control (MPC)-based Reinforcement Learning (RL) offers a structured and interpretable alternative to Deep Neural Network (DNN)-based RL methods.<n>Standard MPC-RL approaches often suffer from slow convergence, suboptimal policy learning due to limited parameterization, and safety issues during online adaptation.<n>We propose a novel framework that integrates MPC-RL with Multi-Objective Bayesian Optimization (MOBO)
  arXiv  Detail & Related papers  (2025-07-14T02:31:52Z)
• A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance [3.4354636842203026]
  We propose PGDA-RL, a primal-dual Projected Gradient Descent-Ascent algorithm for solving regularized Markov Decision Processes (MDPs)<n>PGDA-RL integrates experience replay-based gradient estimation with a two-timescale decomposition of the underlying nested optimization problem.<n>We prove that PGDA-RL converges almost surely to the optimal value function and policy of the regularized MDP.
  arXiv  Detail & Related papers  (2025-05-07T15:18:43Z)
• RL-finetuning LLMs from on- and off-policy data with a single algorithm [53.70731390624718]
  We introduce a novel reinforcement learning algorithm (AGRO) for fine-tuning large-language models.<n>AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies the notion of consistency across any possible generation of the model.<n>We derive algorithms that find optimal solutions via the sample-based policy gradient and provide theoretical guarantees on their convergence.
  arXiv  Detail & Related papers  (2025-03-25T12:52:38Z)
• 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)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)
• Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint [56.74058752955209]
  This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF) We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in strategical exploration of the environment. We propose efficient algorithms with finite-sample theoretical guarantees.
  arXiv  Detail & Related papers  (2023-12-18T18:58:42Z)
• Statistical Rejection Sampling Improves Preference Optimization [42.57245965632205]
  We introduce a novel approach to source preference data from the target optimal policy using rejection sampling. We also propose a unified framework that enhances the loss functions used in both Sequence Likelihood (SLiC) and Direct Preference Optimization (DPO) from a preference modeling standpoint.
  arXiv  Detail & Related papers  (2023-09-13T01:07:25Z)

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.