arXiv research

Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.

Improves imitation learning in RL by learning reward function efficiently.

Robust RL with learned optimal adversary improves agent performance under adversarial state observations.

Adversaries can manipulate cooperative MARL networks.

Deep RL policies are vulnerable to adversarial perturbations, but vanilla training yields more robust policies.

Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning agents assume the adversary either has access to the target agent's learned paramete…

AIRL learns robust, generalizable reward functions from demonstrations.

RADIAL-RL improves deep RL agents' robustness against adversarial attacks.

Attackers can significantly reduce team rewards in cooperative multi-agent reinforcement learning.

Deep RL policies share adversarial features across different MDPs.

Detects adversarial directions to make reinforcement learning policies more robust.

Study on adversarial training's impact on deep neural reinforcement learning policies.

To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment. Existing literature in robust reinforcement learning poses the learning problem as a two player game between the autonomous system…

Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. In this paper we present a novel study into adversarial attacks on deep reinforcement learning polic…

Paper introduces timing-based adversarial attacks on DRL-based navigation systems.

Generative model solves financial market equilibria with stable reinforcement learning.

New approach makes deep reinforcement learning robust without assuming adversary knowledge.

Robust RL improves controller robustness to dynamics variations using adversarial populations.

ARL makes market makers resilient to adversarial conditions.

A new method removes policy optimization in adversarial imitation learning.

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent problems. We study an episodic setting where the parameters of an MDP can differ across…

In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process. In this paper, we introduce Threatened Markov Decision Processes (TMDPs), which provide a framework to support a decision maker against a potential adversary in…

We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best…

New bounds show complexity of adversarial decision making.

RORL improves offline RL robustness with conservative smoothing.

This paper analyzes generalization issues in deep reinforcement learning.

I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, includi…

Adversarial attacks can manipulate deep trading policies, compromising their performance.

This work improves deep reinforcement learning robustness to adversarial state uncertainty.

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial training techniques. In natural language domain, small pertu…

New algorithm identifies near-optimal policies in adversarial distributed RL settings.

Reinforcement learning has seen great advancements in the past five years. The successful introduction of deep learning in place of more traditional methods allowed reinforcement learning to scale to very complex domains achieving super-human performance in environments like the game of Go or numerous video games. Desp…

New framework for robust reinforcement learning policies in uncertain environments.

SAIL improves AIL by weighting adversarial rewards with support estimation.

New method improves DRL robustness against adversarial state observations.

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can lead to degraded performance. We develop a framework for using adversarial deep r…

Adversarial attacks degrade DRL-based EV energy management systems.

The paper evaluates machine learning cyber defenses using log data against adversarial attacks.

Paper robustifies reinforcement learning agents against action space perturbations.

AdMRL improves meta-reinforcement learning by minimizing worst-case sub-optimality gap.

New RL algorithm tackles adversarial RMAB with unknown transitions and bandit feedback.

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy inverse reinforcement learning to learn near-optimal rewards and policies. Empowe…

In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with…

Regularized policies are robust to adversarial rewards.

The paper shows how policy regularization acts like an adversary to improve robustness.

Study efficient reinforcement learning for partially observed systems with linear structure.

This study tackles adversarial corruption in model-based reinforcement learning.

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent's observations. This might lead one to wonder: is it possible to attack an R…