mlsanityData to 7 Oct 2026

ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning

arXiv 2312.07392 ↗First posted 12 Dec 2023cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

While Goal-Conditioned Reinforcement Learning (GCRL) has gained attention, its algorithmic robustness against adversarial perturbations remains unexplored. The attacks and robust representation training methods that are designed for traditional RL become less effective when applied to GCRL. To address this challenge, we first propose the Semi-Contrastive Representation attack, a novel approach inspired by the adversarial contrastive attack. Unlike existing attacks in RL, it only necessitates information from the policy function and can be seamlessly implemented during deployment. Then, to mitigate the vulnerability of existing GCRL algorithms, we introduce Adversarial Representation Tactics, which combines Semi-Contrastive Adversarial Augmentation with Sensitivity-Aware Regularizer to improve the adversarial robustness of the underlying RL agent against various types of perturbations. Extensive experiments validate the superior performance of our attack and defence methods across multiple state-of-the-art GCRL algorithms. Our tool ReRoGCRL is available at https://github.com/TrustAI/ReRoGCRL.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

25 of 37 references.

References · 25

  1. 2017Robust Adversarial Reinforcement Learningcited by 439
  2. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  3. 2017Adversarial Attacks on Neural Network Policiescited by 314
  4. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  5. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  6. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  7. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  8. 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
  9. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 188
  10. 2019Planning with Goal-Conditioned Policiescited by 144
  11. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  12. 2020Adversarial Self-Supervised Contrastive Learningcited by 138
13 more
  1. 2021Goal-Conditioned Reinforcement Learning with Imagined Subgoalscited by 129
  2. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skillscited by 125
  3. 2017Delving into adversarial attacks on deep policiescited by 104
  4. 2020Contrastive Learning with Adversarial Examplescited by 91
  5. 2022Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RLcited by 89
  6. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
  7. 2020Robust Reinforcement Learning via Adversarial training with Langevin Dynamicscited by 45
  8. 2019Model-Based Reinforcement Learning with Adversarial Training for Online Recommendationcited by 33
  9. 2023Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shapingcited by 25
  10. 2020PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goalscited by 21
  11. 2021MHER: Model-based Hindsight Experience Replaycited by 14
  12. 2023Reachability Analysis of Neural Network Control Systemscited by 8
  13. 2023Reward Certification for Policy Smoothed Reinforcement Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2024Boosting Adversarial Training via Fisher-Rao Norm-based Regularizationcited by 7
  2. 2025Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learningcited by 5
  3. 2025Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defensescited by 2
  4. 2026ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoningcited by 2
  5. 2026MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learningcited by 1
  6. 2024Data Augmentation for Continual RL via Adversarial Gradient Episodic Memorycited by 0