Skip to content
Conference

Robust Deep Reinforcement Learning via Adversarial Data Augmentation for Robotic Control Under Observation Uncertainty

Aug 2026 · 2026 3rd International Conference on Intelligent Systems and Robotics (CISR) · pp. 1-9 · 0 citations · 29 references

Abstract

Observation uncertainty can drive a deep reinforcement learning (DRL) controller to select inappropriate actions even when its nominal policy performs well. This issue is especially pronounced in robotic systems deployed outside controlled laboratory conditions, where sensing and communication are affected by noise, bias, and intermittent errors. We introduce robust deep reinforcement learning with adversarial data augmentation (RDRL-ADA), which improves resistance to perturbed observations without sacrificing nominal control quality. The method first augments a standard Markov decision process with an uncertainty set and a state-perturbation mapping. It then instantiates worst-case and stochastic observation-robust formulations for adversarial and random disturbances. To obtain varied training samples, RDRL-ADA alternates between a Bayesian-optimization black-box search and a gradient-based white-box search, and stores intermediate as well as final perturbations in the replay buffer. Policy learning is performed in an off-policy maximum-entropy framework subject to a Tsallis-entropy constraint. Experiments on six MuJoCo control tasks show that the resulting policies maintain stronger performance under observation perturbations and, in most cases, also improve the nominal return over the comparison methods.

View source

Similar papers

#machine learning Preprint Sep 2026

Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization

This work proposes a unified framework, RACER (Risk-sensitive robust Adversarial critic ConsistEncy-regularized Reinforcement learning), that revisits adversarial RL from a risk-sensitive perspective and introduces a state-dependent adversarial objective that adaptively regulates perturbation strength.

Jia-Xin Wu, Tian-Tian Zhang, Yu-Xing Wang et al. · 0 citations
#machine learning Preprint Sep 2026

Robust Policy Optimization via Adversarial Importance Sampling

This work introduces Adversarial Importance Sampling (Advis), a method that uses importance sampling over trajectories from standard training to estimate and optimize verifiable worst-case returns and introduces advrl, a modular PyTorch library that provides clean, single-file implementations of existing robustness met...

Amine Andam, Jamal Bentahar, M. Hedabou · 0 citations
#machine learning Preprint Sep 2026

Provable Benefits of Regularization: Fast Rates for Adversarial Imitation Learning

Dually Regularized AIL is the first algorithm to simultaneously achieve $\widetilde{O}\left(\frac{1}{\epsilon}\right)$ sample complexity in both expert demonstrations and online interactions for this regularized AIL objective, even with stochastic experts.

Hang Zhou, Shang-Zhe Li, А. А. Браверман et al. · 0 citations

Deep Reinforcement Learning with State Uncertainty Estimation for Continuous Control of Dynamic Complex Systems

A Deep Reinforcement Learning framework for Continuous Control with State Uncertainty Estimation based on the Multi-Agent Policy Collaborative Optimization (MAPCO) mechanism is proposed, enabling robust state representation and stable policy optimization through distributed information exchange.

Yuan-Bo Su, Yu Liu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.