Adversarial Attacks on Reinforcement Learning Agents for Command and Control

• URL: http://arxiv.org/abs/2405.01693v2
• Date: Mon, 1 Jul 2024 21:45:52 GMT
• Title: Adversarial Attacks on Reinforcement Learning Agents for Command and Control
• Authors: Ahaan Dabholkar, James Z. Hare, Mark Mittrick, John Richardson, Nicholas Waytowich, Priya Narayanan, Saurabh Bagchi,
• Abstract summary: Recent work has shown that learning based approaches are highly susceptible to adversarial perturbations. In this paper, we investigate the robustness of an agent trained for a Command and Control task in an environment controlled by an adversary. We empirically show that an agent trained using these algorithms is highly susceptible to noise injected by the adversary.
• Score: 6.05332129899857
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the recent impact of Deep Reinforcement Learning in training agents to win complex games like StarCraft and DoTA(Defense Of The Ancients) - there has been a surge in research for exploiting learning based techniques for professional wargaming, battlefield simulation and modeling. Real time strategy games and simulators have become a valuable resource for operational planning and military research. However, recent work has shown that such learning based approaches are highly susceptible to adversarial perturbations. In this paper, we investigate the robustness of an agent trained for a Command and Control task in an environment that is controlled by an active adversary. The C2 agent is trained on custom StarCraft II maps using the state of the art RL algorithms - A3C and PPO. We empirically show that an agent trained using these algorithms is highly susceptible to noise injected by the adversary and investigate the effects these perturbations have on the performance of the trained agent. Our work highlights the urgent need to develop more robust training algorithms especially for critical arenas like the battlefield.

Related papers

• Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environment [1.7403133838762446]
  The complexity of air combat arises from aggressive close-range maneuvers and agile enemy behaviors. In this study, we developed an air combat simulation, which provides noisy observations to the agents. We present a state stacking method for noisy RL environments as a noise reduction technique.
  arXiv  Detail & Related papers  (2023-03-06T12:23:23Z)
• Reinforcement Learning for UAV control with Policy and Reward Shaping [0.7127008801193563]
  This study teaches an RL agent to control a drone using reward-shaping and policy-shaping techniques simultaneously. The results show that an agent trained simultaneously with both techniques obtains a lower reward than an agent trained using only a policy-based approach.
  arXiv  Detail & Related papers  (2022-12-06T14:46:13Z)
• A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform [0.0]
  We proposed a reinforcement learning framework based on Gazebo that is a kind of physical simulation platform (ROS-RL) We used three continuous action space reinforcement learning algorithms in the framework to dealing with the problem of autonomous landing of drones.
  arXiv  Detail & Related papers  (2022-09-07T06:33:57Z)
• Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II [0.5911087507716211]
  In this work, we aim to train deep reinforcement learning agents that can command multiple heterogeneous actors. Our results show that an agent trained via automated curriculum learning can outperform state-of-the-art deep reinforcement learning baselines.
  arXiv  Detail & Related papers  (2022-05-11T21:53:11Z)
• Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents [120.91291581594773]
  We present a formal formulation of a cooperative multi-agent reinforcement learning system with unexpected crashes. We propose a coach-assisted multi-agent reinforcement learning framework, which introduces a virtual coach agent to adjust the crash rate during training. To the best of our knowledge, this work is the first to study the unexpected crashes in the multi-agent system.
  arXiv  Detail & Related papers  (2022-03-16T08:22:45Z)
• Adversary agent reinforcement learning for pursuit-evasion [0.0]
  A reinforcement learning environment with adversary agents is proposed in this work for pursuit-evasion game in the presence of fog of war. One of the most popular learning environments, StarCraft, is adopted here and the associated mini-games are analyzed to identify the current limitation for training adversary agents. The proposed SAAC environment should benefit pursuit-evasion studies with rapidly-emerging reinforcement learning technologies.
  arXiv  Detail & Related papers  (2021-08-25T01:44:06Z)
• Explore and Control with Adversarial Surprise [78.41972292110967]
  Reinforcement learning (RL) provides a framework for learning goal-directed policies given user-specified rewards. We propose a new unsupervised RL technique based on an adversarial game which pits two policies against each other to compete over the amount of surprise an RL agent experiences. We show that our method leads to the emergence of complex skills by exhibiting clear phase transitions.
  arXiv  Detail & Related papers  (2021-07-12T17:58:40Z)
• Disturbing Reinforcement Learning Agents with Corrupted Rewards [62.997667081978825]
  We analyze the effects of different attack strategies based on reward perturbations on reinforcement learning algorithms. We show that smoothly crafting adversarial rewards are able to mislead the learner, and that using low exploration probability values, the policy learned is more robust to corrupt rewards.
  arXiv  Detail & Related papers  (2021-02-12T15:53:48Z)
• Robust Reinforcement Learning on State Observations with Learned Optimal Adversary [86.0846119254031]
  We study the robustness of reinforcement learning with adversarially perturbed state observations. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than previous ones.
  arXiv  Detail & Related papers  (2021-01-21T05:38:52Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)
• Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game [71.24825724518847]
  We present a study on how popular reinforcement learning algorithms can be adapted to learn and to play a real-world implementation of a competitive multiplayer card game. We propose specific training and validation routines for the learning agents, in order to evaluate how the agents learn to be competitive and explain how they adapt to each others' playing style.
  arXiv  Detail & Related papers  (2020-04-08T14:11:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.