Robust Adversarial Policy Optimization Under Dynamics Uncertainty

• URL: http://arxiv.org/abs/2604.10974v2
• Date: Wed, 15 Apr 2026 07:15:04 GMT
• Title: Robust Adversarial Policy Optimization Under Dynamics Uncertainty
• Abstract summary: Reinforcement learning (RL) policies often fail under dynamics that differ from training.<n>We propose a dual formulation that directly exposes the robustness-performance trade-off.<n>The resulting framework, robust adversarial policy optimization (RAPO), outperforms robust RL baselines.
• Score: 8.729531978655737
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Distributionally robust RL provides a formal remedy but still relies on surrogate adversaries to approximate intractable primal problems, leaving blind spots that potentially cause instability and over-conservatism. We propose a dual formulation that directly exposes the robustness-performance trade-off. At the trajectory level, a temperature parameter from the dual problem is approximated with an adversarial network, yielding efficient and stable worst-case rollouts within a divergence bound. At the model level, we employ Boltzmann reweighting over dynamics ensembles, focusing on more adverse environments to the current policy rather than uniform sampling. The two components act independently and complement each other: trajectory-level steering ensures robust rollouts, while model-level sampling provides policy-sensitive coverage of adverse dynamics. The resulting framework, robust adversarial policy optimization (RAPO) outperforms robust RL baselines, improving resilience to uncertainty and generalization to out-of-distribution dynamics while maintaining dual tractability.

Related papers

• IADD-TR: Intervention-Aware Dynamics Decoupling with Targeted Regularization for Model-Based Reinforcement Learning [57.16513298507272]
  We propose IADD-TR, a unified framework combining Intervention-Aware Dynamics Decoupling (IADD) and Targeted Regularization (TR)<n>IADD factorizes transitions into an action-intervention stage and an action-free natural evolution stage, using a zero-action anchor to resolve the non-uniqueness of this two-stage factorization for robust generalization.<n>For policy learning, we derive TR from the efficient influence function of a replay-state policy-gradient functional.
  arXiv  Detail & Related papers  (2026-08-11T08:20:02Z)
• Stationary Robust Mean-Field Games under Model Mismatches [3.053409604085541]
  This paper develops an infinite-horizon, stationary mean-field game framework.<n>It incorporates distributional model uncertainty directly into the population-coupled dynamics.<n>Under a contractive robust-dynamics regime, we obtain explicit non-asymptotic error bounds.
  arXiv  Detail & Related papers  (2026-06-21T16:29:25Z)
• Post-Hoc Robustness for Model-Based Reinforcement Learning [1.4072254177584387]
  This work introduces post-hoc robustification of deep RL agents at inference time.<n>The goal is to improve robustness without any additional training of neural networks.
  arXiv  Detail & Related papers  (2026-06-02T11:43:13Z)
• Robust Regularized Policy Iteration under Transition Uncertainty [6.7431287237221085]
  We formulate offline RL as robust policy optimization, treating the transition kernel as a decision variable within an uncertainty set.<n>We propose Robust Regularized Policy Iteration (RRPI), which replaces the intractable max-min bilevel objective with a tractable KL-regularized surrogate.<n>Experiments on D4RL benchmarks demonstrate that RRPI achieves strong average performance, outperforming recent baselines.
  arXiv  Detail & Related papers  (2026-03-10T08:18:27Z)
• On the Plasticity and Stability for Post-Training Large Language Models [54.757672540381236]
  We identify a root cause as the conflict between plasticity and stability gradients.<n>We propose Probabilistic Conflict Resolution (PCR), a framework that models gradients as random variables.<n>PCR significantly smooths the training trajectory and achieves superior performance in various reasoning tasks.
  arXiv  Detail & Related papers  (2026-02-06T07:31:26Z)
• Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts [68.18666621908898]
  Single-domain offline reinforcement learning (RL) often suffers from limited data coverage.<n>Cross-domain offline RL handles this issue by leveraging additional data from other domains with dynamics shifts.<n>In this paper, we investigate dual (both train-time and test-time) robustness against dynamics shifts in cross-domain offline RL.
  arXiv  Detail & Related papers  (2025-12-02T07:20:39Z)
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping [69.74252624161652]
  We propose BAlanced Policy Optimization with Adaptive Clipping (BAPO)<n>BAPO dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization.<n>On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B.
  arXiv  Detail & Related papers  (2025-10-21T12:55:04Z)
• 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)
• ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty [28.291179179647795]
  We propose textbfAdaptive Rank Representation (AdaRL), a bi-level optimization framework that improves robustness.<n>At the lower level, AdaRL performs policy optimization under fixed-rank constraints with dynamics sampled from a Wasserstein ball around a centroid model.<n>At the upper level, it adaptively adjusts the rank to balance the bias--variance trade-off, projecting policy parameters onto a low-rank manifold.
  arXiv  Detail & Related papers  (2025-10-13T20:05:34Z)
• Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality [53.525547349715595]
  We propose a novel primal-only algorithm called Rectified Robust Policy Optimization (RRPO)<n>RRPO operates directly on the primal problem without relying on dual formulations.<n>We show convergence to an approximately optimal feasible policy with complexity matching the best-known lower bound.
  arXiv  Detail & Related papers  (2025-08-24T16:59:38Z)
• Robust Reinforcement Learning using Adversarial Populations [118.73193330231163]
  Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness. We show that using a single adversary does not consistently yield robustness to dynamics variations under standard parametrizations of the adversary. We propose a population-based augmentation to the Robust RL formulation in which we randomly initialize a population of adversaries and sample from the population uniformly during training.
  arXiv  Detail & Related papers  (2020-08-04T20:57:32Z)

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.