Data to 7 Oct 2026

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

arXiv 2206.10057 ↗First posted 21 Jun 2022cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Despite considerable advances in deep reinforcement learning, it has been shown to be highly vulnerable to adversarial perturbations to state observations. Recent efforts that have attempted to improve adversarial robustness of reinforcement learning can nevertheless tolerate only very small perturbations, and remain fragile as perturbation size increases. We propose Bootstrapped Opportunistic Adversarial Curriculum Learning (BCL), a novel flexible adversarial curriculum learning framework for robust reinforcement learning. Our framework combines two ideas: conservatively bootstrapping each curriculum phase with highest quality solutions obtained from multiple runs of the previous phase, and opportunistically skipping forward in the curriculum. In our experiments we show that the proposed BCL framework enables dramatic improvements in robustness of learned policies to adversarial perturbations. The greatest improvement is for Pong, where our framework yields robustness to perturbations of up to 25/255; in contrast, the best existing approach can only tolerate adversarial noise up to 5/255. Our code is available at: https://github.com/jlwu002/BCL.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 21 Jun 2022.

Builds on

35 of 49 references.

References · 35

2017Proximal Policy Optimization Algorithmscited by 14,441
2014Explaining and Harnessing Adversarial Examplescited by 7,287
2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
2013Intriguing properties of neural networkscited by 5,114
2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
2020Fast is better than free: Revisiting adversarial trainingcited by 723
2019Solving Rubik's Cube with a Robot Handcited by 699
2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698

23 more

2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
2018Certified Defenses against Adversarial Examplescited by 305
2017Noisy Networks for Explorationcited by 262
2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
2018Scaling provable adversarial defensescited by 141
2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
2017Delving into adversarial attacks on deep policiescited by 104
2018Curriculum Adversarial Trainingcited by 89
2020Robust Deep Reinforcement Learning through Adversarial Losscited by 73
2019Defending Against Physically Realizable Attacks on Image Classificationcited by 66
2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
2019Instance adaptive adversarial training: Improved accuracy tradeoffs in neural netscited by 55
2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
2017Synthesizing Robust Adversarial Examplescited by 39
2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
2021Deep reinforcement learning in medical imaging: A literature reviewcited by 34
2020SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothingcited by 26
2020Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learningcited by 23
2017Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Featurescited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 4; 2025: 3; 2026: 1.

15 papers.

Sort:

By area:

2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 22
2023Improve Robustness of Reinforcement Learning against Observation Perturbations via l_∞ Lipschitz Policy Networkscited by 7
2024Verified Safe Reinforcement Learning for Neural Network Dynamic Modelscited by 7
2023Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policycited by 3
2023Robust Multi-agent Communication via Multi-view Message Certificationcited by 3
2024On Minimizing Adversarial Counterfactual Error in Adversarial RLcited by 2
2023Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learningcited by 1
2025Causal-Paced Deep Reinforcement Learningcited by 1
2025Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimizationcited by 1
2022Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attackscited by 0
2023Maneuver Decision-Making Through Automatic Curriculum Reinforcement Learning Without Handcrafted Reward functionscited by 0
2023Robust Offline Reinforcement Learning -- Certify the Confidence Intervalcited by 0

3 more

2024On the Perturbed States for Transformed Input-robust Reinforcement Learningcited by 0
2025Towards Robust Deep Reinforcement Learning against Environmental State Perturbationcited by 0
2026Curriculum reinforcement learning with measurable task representation learningcited by 0