Learning Not to Optimize: Physics-Informed Action-Space Reshaping for Intent-Based Network Control

• URL: http://arxiv.org/abs/2608.00908v1
• Date: Sun, 02 Aug 2026 00:27:01 GMT
• Title: Learning Not to Optimize: Physics-Informed Action-Space Reshaping for Intent-Based Network Control
• Abstract summary: We show that LNOQRD reduces small-instance candidates by $75.9%$ while retaining $90.8%$ near-oracle coverage.<n>Experiments show that LNOQRD achieves the highest utility and intent satisfaction, the lowest hard-law violation and post-generation latency.
• Score: 50.46501177871741
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern network policy control maps intent to sequential placement-control decisions. Bellman-style policy optimization primarily asks which action to optimize, while constraints are commonly handled through penalty, barrier, or Lagrangian mechanisms. We observe that before a value function can certify the best deployment, intermediate signals may already identify many candidates that should be excluded from further optimization. This motivates a complementary direction: \emph{Learning Not to Optimize}. Before a value function is accurate enough to select the best placement-control decision, intermediate signals may already show that candidates are equivalent under state--intent relabeling (quotienting), lead to a uniformly worse future state (dominance), or violate executable network laws (residual screening). \LNOQRD{} uses these computed or learned signals as a shadow process to reshape the domain on which primal policy optimization is performed, thereby reducing the action space. We prove lossless quotienting and dominance under explicit equivariance and monotonicity conditions, bound frontier size and ranking cost, and quantify losses from approximate certificates and primal estimates. Experiments show that \LNOQRD{} reduces small-instance candidates by $75.9\%$ while retaining $90.8\%$ near-oracle coverage and, on large instances, achieves the highest utility and intent satisfaction, the lowest hard-law violation and post-generation latency, and a $73.0\%$ average reduction among candidate-based baselines.

Related papers

• Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates [9.463718838347955]
  We propose a novel optimistic online mirror descent that utilizes safeguarded large learning rates up to $(T)$.<n>Our key technical contribution is a post-hoc penalty mechanism that dynamically monitors unstable updates and excludes learning rates incurring excessive regret.<n> Empirical evaluations on three synthetic and eleven diverse real-world datasets demonstrate that our approach reduces the adaptation lag from hundreds of rounds to a few rounds.
  arXiv  Detail & Related papers  (2026-05-26T12:18:08Z)
• One-Way Policy Optimization for Self-Evolving LLMs [63.8638342097375]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become a promising paradigm for scaling reasoning capabilities of Large Language Models (LLMs)<n>We propose One-Way Policy Optimization (OWPO), a method based on the principle of decoupling optimization direction from update magnitude.<n> Experimental results demonstrate that OWPO outperforms strong baselines, including DAPO, OPD, and MOPD.
  arXiv  Detail & Related papers  (2026-05-21T08:25:27Z)
• Primal-Dual Policy Optimization for Linear CMDPs with Adversarial Losses [0.8984888893275712]
  We introduce and run with a new class of policies, which we call weighted LogSumExp softmax policies.<n>Two novel algorithmic components -- periodic policy mixing and a regularized dual update -- allow us to effectively control both the covering number and the dual variable.
  arXiv  Detail & Related papers  (2026-05-12T05:02:02Z)
• Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization [18.737087162461563]
  Test-time compute scaling has become a powerful lever for improving large language model performance.<n>Yet deploying these techniques under finite inference budgets requires a decision that current systems largely ignore.<n>We formalize this as a constrained optimization problem (maximize expected accuracy subject to an average compute budget) and solve it with a two-stage Solve-then-Learn pipeline.
  arXiv  Detail & Related papers  (2026-04-16T10:39:22Z)
• Accelerating RL for LLM Reasoning with Optimal Advantage Regression [52.0792918455501]
  We propose a novel two-stage policy optimization framework that directly approximates the optimal advantage function.<n>$A$*-PO achieves competitive performance across a wide range of mathematical reasoning benchmarks.<n>It reduces training time by up to 2$times$ and peak memory usage by over 30% compared to PPO, GRPO, and REBEL.
  arXiv  Detail & Related papers  (2025-05-27T03:58:50Z)
• Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment [54.787826863212146]
  Inference-time computation offers a powerful axis for scaling the performance of language models.<n>We analyze the performance of inference-time alignment algorithms in terms of (i) response quality, and (ii) compute.<n>We introduce $textttInferenceTimePessimism$, a new algorithm which mitigates reward hacking through deliberate use of inference-time compute.
  arXiv  Detail & Related papers  (2025-03-27T18:00:08Z)
• Spatial Supply Repositioning with Censored Demand Data [10.797160099834306]
  We consider a network inventory system motivated by one-way, on-demand vehicle sharing services.<n>Finding an optimal policy in such a general inventory network is analytically and computationally challenging.<n>Our work highlights the critical role of inventory in the viability of shared mobility businesses.
  arXiv  Detail & Related papers  (2025-01-31T15:16:02Z)
• Learning to Cover: Online Learning and Optimization with Irreversible Decisions [50.5775508521174]
  We define an online learning and optimization problem with discrete and irreversible decisions contributing toward a coverage target.<n>In each period, a decision-maker selects facilities to open, receives information on the success of each one, and updates a classification model to guide future decisions.<n>The goal is to minimize facility openings under a chance constraint reflecting the coverage target, in an horizon regime characterized by a large target number of facilities.
  arXiv  Detail & Related papers  (2024-06-20T23:00:25Z)
• 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)
• Submodular Reinforcement Learning [38.40138241424851]
  In reinforcement learning (RL), rewards of states are typically considered additive, and following the Markov assumption, they are $textitindependent$ states visited previously. In many important applications, such as coverage control, experiment design and informative path planning, rewards naturally have diminishing returns, i.e., their value decreases in light of similar states visited previously. We propose $textitsubmodular RL$ (SubRL), a paradigm which seeks to optimize more general, non-additive (and history-dependent) rewards modelled via submodular set functions which capture diminishing returns
  arXiv  Detail & Related papers  (2023-07-25T09:46:02Z)
• A Generalised Inverse Reinforcement Learning Framework [24.316047317028147]
  inverse Reinforcement Learning (IRL) is to estimate the unknown cost function of some MDP base on observed trajectories. We introduce an alternative training loss that puts more weights on future states which yields a reformulation of the (maximum entropy) IRL problem. The algorithms we devised exhibit enhanced performances (and similar tractability) than off-the-shelf ones in multiple OpenAI gym environments.
  arXiv  Detail & Related papers  (2021-05-25T10:30:45Z)

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.