mlsanityData to 7 Oct 2026

Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)

arXiv 2109.14678 ↗First posted 29 Sep 2021cs.LG cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from observed behavior. In this paper, we propose Constrained Randomization of Policy (CRoP) as a mitigation technique against such attacks. CRoP induces the execution of sub-optimal actions at random under performance loss constraints. We present a parametric analysis of CRoP, address the optimality of CRoP, and establish theoretical bounds on the adversarial budget and the expectation of loss. Furthermore, we report the experimental evaluation of CRoP in Atari environments under adversarial imitation, which demonstrate the efficacy and feasibility of our proposed method against policy replication attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 8 of its 15 references that are in the map. First posted on arXiv 29 Sep 2021.

Builds on

8 of 15 references.

Closest ancestors · 1

Same direction, newest first

  1. 2019Imitation Learning as f-Divergence Minimization30 May

Other references · 7

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2020Stealing Deep Reinforcement Learning Models for Fun and Profitcited by 24
  4. 2019Adversarial Exploitation of Policy Imitationcited by 13
  5. 2019Sequential Triggers for Watermarking of Deep Reinforcement Learning Policiescited by 7
  6. 2018The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learningcited by 5
  7. 2020PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2020Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization
  2. 2022Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games
  3. 2020Adversarial Imitation Learning via Random Search
  4. 2024Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
  5. 2024Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
  6. 2020Preventing Imitation Learning with Adversarial Policy Ensembles
  7. 2024Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof
  8. 2024Stealthy Imitation: Reward-guided Environment-free Policy Stealing