Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization

• URL: http://arxiv.org/abs/2605.12771v1
• Date: Tue, 12 May 2026 21:32:57 GMT
• Title: Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization
• Abstract summary: Multi- curvature reinforcement learning in domains requires balancing complex, non-fragile interference trade-offs between conflicting objectives.<n>In this paper we introduce a novel based real-time based real-time optimization on a robotic visual -- a proxy for monitoring ecosystems.
• Score: 55.338784037660474
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-objective reinforcement learning in robotic domains requires balancing complex, non-convex trade-offs between conflicting objectives. While linear scalarization methods provide stability, they are theoretically incapable of recovering solutions within non-convex regions of the Pareto front. Conversely, static non-linear scalarizations (e.g., Tchebycheff) can theoretically access these regions but often suffer from severe gradient variance and optimization instability in deep RL. In this work, we propose an Adaptive Smooth Tchebycheff framework that resolves this tension by dynamically modulating the curvature of the optimization landscape. We introduce a novel conflict-driven controller that regulates the optimization smoothness based on real-time gradient interference. This allows the agent to anneal toward precise, non-convex scalarization when objectives align, while elastically reverting to stable, smooth approximations when destructive gradient conflicts emerge. We validate our approach on a challenging robotic stealth visual search task -- a proxy for monitoring of protected/fragile ecosystems -- where an agent must balance search, exposure/interference minimization and exploration speed. Extensive ablations confirm that our conflict-aware adaptation enables the robust discovery of Pareto-optimal policies in non-convex regions inaccessible to linear baselines and unstable for static non-linear methods. Website: https://alejandromllo.github.io/research/pasta/

Related papers

• GPU-Parallel Linearization Error Bounds for Real-Time Robust Optimal Control of Nonlinear and Neural Network Dynamics [3.9198548406564595]
  This paper studies real-time robust optimal control for uncertain nonlinear systems, where linear time-varying (LTV) approximations make planning tractable but require sound linearization error bounds (LEBs) to guarantee robust constraint satisfaction.<n>We develop tight, differentiable, GPU-parallel LEBs for LTV approximations of nonlinear and neural network (NN) dynamics.<n>Our method can compute robust control policies on the GPU at rates up to 67 Hz, reducing solve times and conservativeness relative to baselines while preserving formal guarantees and real-time performance.
  arXiv  Detail & Related papers  (2026-07-01T17:42:37Z)
• Fitting Unknown Number of Hyperplanes with Manifold Optimization [57.48093263119306]
  Fitting unknown number of linearplanes to data is a fundamental yet challenging problem in machine learning.<n>Existing approaches often struggle with optimum optima or lack geometric consistency.
  arXiv  Detail & Related papers  (2026-05-27T14:02:20Z)
• Iterative Convex Optimization with Control Barrier Functions for Obstacle Avoidance among Polytopes [3.8436274588467696]
  Obstacle avoidance by polytopic robots is a challenging problem in optimization-based control and trajectory planning.<n>Existing methods rely on hyperiable distance approximations, such as ellipsoids, which distort geometric dynamics.<n>In this paper, we propose a novel iterative convexity- finite-horizon optimization framework for safety-critical navigation programs.
  arXiv  Detail & Related papers  (2026-03-06T05:10:44Z)
• BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning [49.25750348525603]
  BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions into dynamic, probability-aware clipping intervals.<n>We show that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.
  arXiv  Detail & Related papers  (2026-03-05T08:03:05Z)
• Steerable Adversarial Scenario Generation through Test-Time Preference Alignment [58.37104890690234]
  Adversarial scenario generation is a cost-effective approach for safety assessment of autonomous driving systems.<n>We introduce a new framework named textbfSteerable textbfAdversarial scenario textbfGEnerator (SAGE)<n>SAGE enables fine-grained test-time control over the trade-off between adversariality and realism without any retraining.
  arXiv  Detail & Related papers  (2025-09-24T13:27:35Z)
• Online Stackelberg Optimization via Nonlinear Control [11.220642401065495]
  In repeated interaction problems with adaptive agents, our objective often requires anticipating and optimizing over the space of possible agent responses. We show that many problems of this form can be cast as instances of online (nonlinear) control which satisfy textitlocal controllability, with convex losses over a bounded state space. We introduce a unified algorithmic framework for tractable regret minimization in such cases.
  arXiv  Detail & Related papers  (2024-06-27T00:42:33Z)
• An Adaptive Fuzzy Reinforcement Learning Cooperative Approach for the Autonomous Control of Flock Systems [4.961066282705832]
  This work introduces an adaptive distributed robustness technique for the autonomous control of flock systems. Its relatively flexible structure is based on online fuzzy reinforcement learning schemes which simultaneously target a number of objectives. In addition to its resilience in the face of dynamic disturbances, the algorithm does not require more than the agent position as a feedback signal.
  arXiv  Detail & Related papers  (2023-03-17T13:07:35Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear System [4.3012765978447565]
  We propose a parameterization of nonlinear output feedback controllers for linear dynamical systems. Our approach guarantees the closed-loop stability of partially observable linear dynamical systems without requiring any constraints to be satisfied.
  arXiv  Detail & Related papers  (2021-12-08T10:43:47Z)
• Improper Learning with Gradient-based Policy Optimization [62.50997487685586]
  We consider an improper reinforcement learning setting where the learner is given M base controllers for an unknown Markov Decision Process. We propose a gradient-based approach that operates over a class of improper mixtures of the controllers.
  arXiv  Detail & Related papers  (2021-02-16T14:53:55Z)
• Robust Reinforcement Learning with Wasserstein Constraint [49.86490922809473]
  We show the existence of optimal robust policies, provide a sensitivity analysis for the perturbations, and then design a novel robust learning algorithm. The effectiveness of the proposed algorithm is verified in the Cart-Pole environment.
  arXiv  Detail & Related papers  (2020-06-01T13:48:59Z)

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.