Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution

• URL: http://arxiv.org/abs/2509.14816v1
• Date: Thu, 18 Sep 2025 10:18:07 GMT
• Title: Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution
• Authors: Humphrey Munn, Brendan Tidd, Peter Böhm, Marcus Gallagher, David Howard,
• Abstract summary: We show how to resolve conflicts between task-based rewards and terms that regularise the policy towards realistic behaviour.<n>We propose GCR-PPO, a modification to actor-critic optimisation that decomposes the actor update into objective-wise gradients.<n>GCR-PPO improves on large-scale proximal policy optimisation with an average improvement of 9.5%, with high-conflict tasks observing a greater improvement.
• Score: 2.359524447776588
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning (RL) robot controllers usually aggregate many task objectives into one scalar reward. While large-scale proximal policy optimisation (PPO) has enabled impressive results such as robust robot locomotion in the real world, many tasks still require careful reward tuning and are brittle to local optima. Tuning cost and sub-optimality grow with the number of objectives, limiting scalability. Modelling reward vectors and their trade-offs can address these issues; however, multi-objective methods remain underused in RL for robotics because of computational cost and optimisation difficulty. In this work, we investigate the conflict between gradient contributions for each objective that emerge from scalarising the task objectives. In particular, we explicitly address the conflict between task-based rewards and terms that regularise the policy towards realistic behaviour. We propose GCR-PPO, a modification to actor-critic optimisation that decomposes the actor update into objective-wise gradients using a multi-headed critic and resolves conflicts based on the objective priority. Our methodology, GCR-PPO, is evaluated on the well-known IsaacLab manipulation and locomotion benchmarks and additional multi-objective modifications on two related tasks. We show superior scalability compared to parallel PPO (p = 0.04), without significant computational overhead. We also show higher performance with more conflicting tasks. GCR-PPO improves on large-scale PPO with an average improvement of 9.5%, with high-conflict tasks observing a greater improvement. The code is available at https://github.com/humphreymunn/GCR-PPO.

Related papers

• Balancing Multiple Objectives in Urban Traffic Control with Reinforcement Learning from AI Feedback [14.81819959351561]
  We show that multi-objective RLAIF can produce policies that yield balanced trade-offs reflecting different user priorities without laborious reward engineering.<n>We argue that integrating RLAIF into multi-objective RL offers a scalable path toward user-aligned policy learning.
  arXiv  Detail & Related papers  (2026-02-24T09:47:25Z)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• Multi-Agent Reinforcement Learning and Real-Time Decision-Making in Robotic Soccer for Virtual Environments [0.0]
  This paper presents a unified Multi-Agent Reinforcement Learning (MARL) framework that addresses these challenges.<n>To ensure scalability, we integrate mean-field theory into the HRL framework.<n>Our mean-field actor-critic method achieves a significant performance boost.
  arXiv  Detail & Related papers  (2025-12-02T19:11:44Z)
• Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation [8.50468505606714]
  We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL)<n>This problem arises in applications such as robotics, control, and preference optimization in language models.<n>We introduce a two-stage procedure -- meta-training followed by fine-tuning -- to address this problem.
  arXiv  Detail & Related papers  (2025-11-16T21:05:21Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Perception-Aware Policy Optimization for Multimodal Reasoning [79.56070395437898]
  A major source of error in current multimodal reasoning lies in the perception of visual inputs.<n>We propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason.<n>We observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO.
  arXiv  Detail & Related papers  (2025-07-08T23:22:34Z)
• Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach [2.8626097661711394]
  Reinforcement Learning from Human Feedback has achieved notable success in steering models, but is complex and can be unstable.<n>Recent approaches such as Direct Preference Optimization (DPO) simplify preference-based fine-tuning but may introduce bias or trade-off certain objectives.<n>We propose a Group Relative Policy Optimization framework with a multi-label reward regression model to achieve safe and aligned language generation.
  arXiv  Detail & Related papers  (2025-03-26T05:50:33Z)
• The Perfect Blend: Redefining RLHF with Mixture of Judges [68.58426626501883]
  Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM) Applying RLHF for MTL currently requires careful tuning of the weights for reward model and data combinations. We introduce a novel post-training paradigm which we called Constrained Generative Policy Optimization (CGPO)
  arXiv  Detail & Related papers  (2024-09-30T15:06:53Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• Enhancing Robotic Navigation: An Evaluation of Single and Multi-Objective Reinforcement Learning Strategies [0.9208007322096532]
  This study presents a comparative analysis between single-objective and multi-objective reinforcement learning methods for training a robot to navigate effectively to an end goal. By modifying the reward function to return a vector of rewards, each pertaining to a distinct objective, the robot learns a policy that effectively balances the different goals.
  arXiv  Detail & Related papers  (2023-12-13T08:00:26Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)

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.