Disturbing Reinforcement Learning Agents With Corrupted Rewards

Abstract

Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In the side of the drawbacks, recent works have shown how the performance of RL algorithms decreases under the influence of soft changes in the reward function. However, little work has been done about how sensitive these disturbances are depending on the aggressiveness of the attack and the learning exploration strategy. In this paper, we propose to fill this gap in the literature analyzing the effects of different attack strategies based on reward perturbations, and studying the effect in the learner depending on its exploration strategy. In order to explain all the behaviors, we choose a sub-class of MDPs: episodic, stochastic goal-only-rewards MDPs, and in particular, an intelligible grid domain as a benchmark. In this domain, we demonstrate that smoothly crafting adver

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymajadas2021disturbing

Related papers

• Reinforcement Learning With Perturbed Rewards (2018)13.74
• The Distributional Reward Critic Framework For Reinforcement Learning Under Perturbed Rewards (2024)0.00
• Provably Invincible Adversarial Attacks On Reinforcement Learning Systems: A Rate-distortion Information-theoretic Approach (2025)0.00
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Efficient Reward Poisoning Attacks On Online Deep Reinforcement Learning (2022)0.00
• Understanding The Limits Of Poisoning Attacks In Episodic Reinforcement Learning (2022)3.58
• Optimal Attack And Defense For Reinforcement Learning (2023)6.34
• Reward Tampering Problems And Solutions In Reinforcement Learning: A Causal Influence Diagram Perspective (2019)0.00