PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning

• URL: http://arxiv.org/abs/2603.19579v1
• Date: Fri, 20 Mar 2026 02:46:46 GMT
• Title: PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning
• Abstract summary: We propose the PA2D-MORL method, which constructs an efficient scheme for multi-objective problem decomposition and policy improvement.<n>We show that the proposed method clearly outperforms the current state-of-the-art algorithm in terms of both quality and stability of the outcomes.
• Score: 17.67661165622871
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Multi-objective reinforcement learning (MORL) provides an effective solution for decision-making problems involving conflicting objectives. However, achieving high-quality approximations to the Pareto policy set remains challenging, especially in complex tasks with continuous or high-dimensional state-action space. In this paper, we propose the Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning (PA2D-MORL) method, which constructs an efficient scheme for multi-objective problem decomposition and policy improvement, leading to a superior approximation of Pareto policy set. The proposed method leverages Pareto ascent direction to select the scalarization weights and computes the multi-objective policy gradient, which determines the policy optimization direction and ensures joint improvement on all objectives. Meanwhile, multiple policies are selectively optimized under an evolutionary framework to approximate the Pareto frontier from different directions. Additionally, a Pareto adaptive fine-tuning approach is applied to enhance the density and spread of the Pareto frontier approximation. Experiments on various multi-objective robot control tasks show that the proposed method clearly outperforms the current state-of-the-art algorithm in terms of both quality and stability of the outcomes.

Related papers

• Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization [54.855135506924775]
  We introduce a two-stage multi-objective optimization framework for aligning tool-using large language models (LLMs) under competing objectives.<n>This design enables fine-grained, action-level optimization across multiple conflicting objectives.
  arXiv  Detail & Related papers  (2026-06-15T01:58:07Z)
• QoS-Aware Hierarchical Reinforcement Learning for Joint Link Selection and Trajectory Optimization in SAGIN-Supported UAV Mobility Management [52.15690855486153]
  A space-air-ground integrated network (SAGIN) has emerged as an essential architecture for enabling ubiquitous UAV connectivity.<n>This paper formulates UAV mobility management in SAGIN as a constrained multiobjective joint optimization problem.
  arXiv  Detail & Related papers  (2025-12-17T06:22:46Z)
• A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks [4.166623313248681]
  A set of optimal solutions approximates the Pareto set.<n>Some current methods face a challenge: how to make the solution diverse while maximizing the hypervolume value.<n>In this paper, we propose a novel method to address this challenge, which employs Stein Variational Gradient Descent.
  arXiv  Detail & Related papers  (2025-06-07T08:50:42Z)
• Pareto Set Learning for Multi-Objective Reinforcement Learning [19.720934024901542]
  We propose a decomposition-based framework for Multi-Objective RL (MORL)<n>PSL-MORL harnesses the generation capability of hypernetwork to produce the parameters of the policy network for each decomposition weight.<n>We show that PSL-MORL significantly outperforms state-of-the-art MORL methods in the hypervolume and sparsity indicators.
  arXiv  Detail & Related papers  (2025-01-12T10:43:05Z)
• Policy Gradient for Robust Markov Decision Processes [16.281897051782863]
  This paper introduces a novel policy gradient method, Double-Loop Robust Policy Mirror Descent (MD), for solving robust Markov Decision Processes (MDPs) MD employs a general mirror descent update rule for the policy optimization with adaptive tolerance per iteration, guaranteeing convergence to a globally optimal policy. We provide a comprehensive analysis of MD, including new convergence results under both direct and softmax parameterizations, and provide novel insights into the inner problem solution through Transition Mirror Ascent (TMA)
  arXiv  Detail & Related papers  (2024-10-29T15:16:02Z)
• Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs [82.34567890576423]
  We develop a deterministic policy gradient primal-dual method to find an optimal deterministic policy with non-asymptotic convergence.<n>We prove that the primal-dual iterates of D-PGPD converge at a sub-linear rate to an optimal regularized primal-dual pair.<n>This appears to be the first work that proposes a deterministic policy search method for continuous-space constrained MDPs.
  arXiv  Detail & Related papers  (2024-08-19T14:11:04Z)
• UCB-driven Utility Function Search for Multi-objective Reinforcement Learning [51.00436121587591]
  In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours.<n>We focus on the case of linear utility functions parametrised by weight vectors w.<n>We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process.
  arXiv  Detail & Related papers  (2024-05-01T09:34:42Z)
• Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning [13.245000585002858]
  In many real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. We propose a constrained multi-objective gradient aggregation algorithm named Constrained Multi-Objective Gradient Aggregator (CoGAMO)
  arXiv  Detail & Related papers  (2024-03-01T04:57:13Z)
• Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning [5.897578963773195]
  We introduce Iterated Pareto Referent optimisation (IPRO)<n>IPRO decomposes finding the Pareto front into a sequence of constrained single-objective problems.<n>By leveraging problem-specific single-objective solvers, our approach holds promise for applications beyond multi-objective reinforcement learning.
  arXiv  Detail & Related papers  (2024-02-11T12:35:13Z)
• A Robust Policy Bootstrapping Algorithm for Multi-objective Reinforcement Learning in Non-stationary Environments [15.794728813746397]
  Multi-objective reinforcement learning methods fuse the reinforcement learning paradigm with multi-objective optimization techniques. One major drawback of these methods is the lack of adaptability to non-stationary dynamics in the environment. We propose a novel multi-objective reinforcement learning algorithm that can robustly evolve a convex coverage set of policies in an online manner in non-stationary environments.
  arXiv  Detail & Related papers  (2023-08-18T02:15:12Z)
• Acceleration in Policy Optimization [50.323182853069184]
  We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates. We define optimism as predictive modelling of the future behavior of a policy, and adaptivity as taking immediate and anticipatory corrective actions to mitigate errors from overshooting predictions or delayed responses to change. We design an optimistic policy gradient algorithm, adaptive via meta-gradient learning, and empirically highlight several design choices pertaining to acceleration, in an illustrative task.
  arXiv  Detail & Related papers  (2023-06-18T15:50:57Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)

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.