Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)

2019-06-03 · Vahid Behzadan, William Hsu

This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a formal analysis of adversarial training in DQN agents and its performance with respect to the proportion of adversarial perturbations to nominal observations used for training. Next, we consider the sample-inefficiency of current adversarial training techniques, and propose a novel Adversarially-Guided Exploration (AGE) mechanism based on a modified hybrid of the $\epsilon$-greedy algorithm and Boltzmann exploration. We verify the feasibility of this exploration mechanism through experimental evaluation of its performance in comparison with the traditional decaying $\epsilon$-greedy and parameter-space noise exploration algorithms.

📄 PDF Abstract BibTeX arXiv:1906.01119

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Post-Hoc Robustness for Model-Based Reinforcement Learning

2026-06-02 · Siemen Herremans, Ali Anwar, Siegfried Mercelis arxiv

To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversarial environment perturbations. In this setting, a protagonist agent o…

Reinforcement Learning

Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models

2019-05-13 · Mayank Singh, Abhishek Sinha, Nupur Kumari, Harshitha Machiraju 외

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adver…

Adversarial Attack

Adversarially Trained Neural Policies in the Fourier Domain

2021-06-18 · ICML Workshop AML 2021 7 · Ezgi Korkmaz

Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer

2025-02-06 · Yulun Wu, Doron L. Bergman

We present an Adversarially Pre-trained Transformer (APT) that is able to perform zero-shot meta-learning on tabular prediction tasks without pre-training on any real-world dataset, extending on the recent development of…

Meta-Learning Missing Values

Resilient Leader-Follower Consensus with Time-Varying Leaders in Discrete-Time Systems

2019-06-19

The problem of consensus in the presence of adversarially behaving agents has been studied extensively in the literature. The proposed algorithms typically guarantee that the consensus value lies within the convex hull o…