Forcement Learning Agents

نویسندگان

  • Yen-Chen Lin
  • Zhang-Wei Hong
  • Yuan-Hong Liao
  • Meng-Li Shih
  • Ming-Yu Liu
  • Min Sun
چکیده

We introduce two novel tactics for adversarial attack on deep reinforcement learning (RL) agents: strategically-timed and enchanting attack. For strategicallytimed attack, our method selectively forces the deep RL agent to take the least likely action. For enchanting attack, our method lures the agent to a target state by staging a sequence of adversarial attacks. We show that DQN and A3C agents are vulnerable to both tactics. Future work on defending is discussed in App. C.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Adaptive neuro-fuzzy modeling applied to policy gradient reinforcement learning

-Function approximation has been used extensively with rein forcement learning, even though theoretical support was based mainly on tabular representations. This paper proposes an actor-critic structure following the existing convergence proofs as much as possible. The actor and critic modules employ an adaptive neuro-fuzzy architecture based on fuzzy ARTMAP concepts and gradient descent. Resul...

متن کامل

An on-line algorithm for dynamic reinforcement learning and planning in reactive environments

An on line learning algorithm for reinforcement learning with continually running recur rent networks in non stationary reactive environments is described Various kinds of rein forcement are considered as special types of input to an agent living in the environment The agent s only goal is to maximize the amount of reinforcement received over time Supervised learning techniques for recurrent ne...

متن کامل

Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents

This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

متن کامل

A Sensory Control System for Adjusting Group Emotion Using Bayesian Networks and Reinforcement Learning

The relationship between sensory stimuli and emotion has been actively investigated, but it is relatively undisclosed to determine appropriate stimuli for inducing the target emotion for a group of people in the same space like school, hospital, store, etc. In this paper, we propose a stimuli control system to adjust group emotion in a closed space, especially kindergarten. The proposed system ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017