A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Generative Adversarial Exploration for Reinforcement Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel. ...
In this paper, we propose a novel method called generative adversarial exploration (GAEX) to encourage exploration in RL via introducing an intrinsic reward output from a generative adversarial network ...
CONCLUSION This paper provides a novel exploration framework, Generative Adversarial Exploration (GAEX), to address the exploration-exploitation dilemma in deep reinforcement learning. ...
arXiv:2201.11685v1
fatcat:xseso2ciaffijczbc573vnigqi
Risk Averse Robust Adversarial Reinforcement Learning
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper we introduce risk-averse robust adversarial reinforcement learning (RARARL), using a risk-averse protagonist and a risk-seeking adversary. ...
A classical technique for improving the robustness of reinforcement learning algorithms is to train on a set of randomized environments, but this approach only guards against common situations. ...
More generally, robustness and safety have long been explored in reinforcement learning [21] , [22] , [23] . Chow et al. ...
arXiv:1904.00511v1
fatcat:5jwf2nreefe7bjgpli7leupazi
DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, ...
We recast adversarial text example generation as a reinforcement learning problem, and demonstrate that our algorithm offers preliminary but promising steps towards generating semantically meaningful adversarial ...
Acknowledgments Many thanks to Will Monroe for his crackerjack adversarial text generation advice and expertise, and for sharing an alarming series of articles about 3D-printed turtles misclassified as ...
arXiv:1712.05419v1
fatcat:ccrkfg4nargw3hctkdi6iispym
Deep Adversarial Reinforcement Learning for Object Disentangling
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To solve this problem, we present a novel adversarial reinforcement learning (ARL) framework. ...
Deep learning in combination with improved training techniques and high computational power has led to recent advances in the field of reinforcement learning (RL) and to successful robotic RL applications ...
We present a novel adversarial learning framework for reinforcement learning algorithms: Adversarial reinforcement learning (ARL). ...
arXiv:2003.03779v2
fatcat:ekewmbpqi5bitiw2y34tkppnui
LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification
2019
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Due to the discrete generation step in the generator, we use policy gradient, a reinforcement learning approach, to train the two modules. ...
The proposed approach consists of a generator and a classifier. The generator learns to generate examples to attack the classifier while the classifier learns to defend these attacks. ...
Acknowledgments We thank all reviewers for providing the thoughtful and constructive suggestions. This work was supported in part by National Natural Science Foundation of China (No. 61673028). ...
doi:10.18653/v1/d19-1554
dblp:conf/emnlp/XuZYZLS19
fatcat:czux2pcmp5dwdczl4t7xbt2c5e
Adaptive perturbation adversarial training: based on reinforcement learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This paper proposes a method for finding marginal adversarial samples based on reinforcement learning, and combines it with the latest fast adversarial training technology, which effectively speeds up ...
However, searching for marginal adversarial samples brings additional computational costs. ...
Algorithm 1 describes the marginal adversarial sample search based on reinforcement learning. ...
arXiv:2108.13239v1
fatcat:t5z5jshnybd37f75txuwwkczxy
MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
MedAttacker addresses the challenges brought by EHR data via two steps: hierarchical position selection which selects the attacked positions in a reinforcement learning (RL) framework and substitute selection ...
In addition, based on the experiment results we include a discussion on defending EHR adversarial attacks. ...
Thus, in this complex situation, MedAttacker is able to bring out the potential of reinforcement learning and generate more adversarial examples to successfully fool the victim models. ...
arXiv:2112.06063v1
fatcat:jiiues7sere6lfjs2x2d76vy5m
Adversarial recovery of agent rewards from latent spaces of the limit order book
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. ...
In this paper, we explore whether adversarial inverse RL algorithms can be adapted and trained within such latent space simulations from real market data, while maintaining their ability to recover agent ...
Adversarial learning from Reinforcement Learning trading experts As in general GAN structures, adversarial inverse reinforcement learning is implemented through a generator and a discriminator: two neural ...
arXiv:1912.04242v1
fatcat:zfbo3bhxc5akzjvdgisb2ib3f4
Solving reward-collecting problems with UAVs: a comparison of online optimization and Q-learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We present a comparison of three methods to solve this problem: namely we implement a Deep Q-Learning model, an ε-greedy tabular Q-Learning model, and an online optimization framework. ...
As the prevalence of UAVs increases, there has also been improvements in counter-UAV technology that makes it difficult for them to successfully obtain valuable intelligence within an area of interest. ...
Erich Morman: Modeled and implemented the ε-greedy tabular Q-Learning. Additionally conducted computational experiments using -Q learning. ...
arXiv:2112.00141v1
fatcat:motshvd4qrfvphe2hnoppyib4q
Domain Adaptation for Reinforcement Learning on the Atari
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
This is borne out by the fact that a reinforcement learning agent has no prior knowledge of the world, no pre-existing data to depend on and so must devote considerable time to exploration. ...
We demonstrate that this initialisation step provides significant improvement when learning a new reinforcement learning task, which highlights the wide applicability of adversarial adaptation methods; ...
Conclusion We have presented an adversarial method for knowledge transfer in reinforcement learning. ...
arXiv:1812.07452v1
fatcat:mdhunianpjdvbn2u6nmqrxn7ta
Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This paper presents a new method --- adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems. ...
Inspired by generative adversarial networks (GAN), we train a discriminator to differentiate responses/actions generated by dialogue agents from responses/actions by experts. ...
Ho and Ermon also drew a connection between inverse reinforcement learning and generative adversarial networks to learn the reward function in the GAN framework [23] . ...
arXiv:1710.11277v2
fatcat:sydo2iblv5d6fmip5pxfpvwakq
A Reinforced Generation of Adversarial Examples for Neural Machine Translation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Instead of collecting and analyzing bad cases using limited handcrafted error features, here we investigate this issue by generating adversarial examples via a new paradigm based on reinforcement learning ...
The results show that our method efficiently produces stable attacks with meaning-preserving adversarial examples. ...
Acknowledgement We would like to thank the anonymous reviewers for their insightful comments. Shujian Huang is the corresponding author. ...
arXiv:1911.03677v2
fatcat:pdc76yp2trhgnffths76i4unce
Adversarial attack and defense in reinforcement learning-from AI security view
2019
Cybersecurity
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Reinforcement learning is a core technology for modern artificial intelligence, and it has become a workhorse for AI applications ranging from Atrai Game to Connected and Automated Vehicle System (CAV) ...
Hence, in this paper, we give the very first attempt to conduct a comprehensive survey on adversarial attacks in reinforcement learning under AI security. ...
applications in AI. ( I) They gave the very first attempt to prove that reinforcement learning systems are vulnerable to adversarial attack, and the traditional generation algorithms designed for adversarial ...
doi:10.1186/s42400-019-0027-x
fatcat:nlox7arfojaerietjz5ipskucm
Adversarial Deep Reinforcement Learning based Adaptive Moving Target Defense
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Based on an established model of adaptive MTD, we propose a multi-agent reinforcement learning framework based on the double oracle algorithm to solve the game. ...
Finding an optimal strategy for MTD presents a significant challenge, especially when facing a resourceful and determined adversary who may respond to the defender's actions. ...
In general, traditional reinforcement learning techniques use tabular approaches to store estimated rewards (e.g., Q-Learning) [11] . ...
arXiv:1911.11972v2
fatcat:qszyzcpwvba3fmwrd3qjtyvefe
Adversarial Attacks on Neural Network Policies
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we show adversarial attacks are also effective when targeting neural network policies in reinforcement learning. ...
We characterize the degree of vulnerability across tasks and training algorithms, for a subclass of adversarial-example attacks in white-box and black-box settings. ...
Transferability Across Policies To explore transferability of adversarial examples across policies, we generate adversarial perturbations for the target policy using one of the other top-performing policies ...
arXiv:1702.02284v1
fatcat:iszu636xnjedxe2ponhr7tuxiu
« Previous
Showing results 1 — 15 out of 35,860 results