New Zealand

Kunikazu Kobayashi, Koji Nakano, Takashi Kuremoto and Masanao Obayashi (February 1st 2010). Objective-based Reinforcement Learning System for Cooperative Behavior Acquisition, Application of Machine Learning, Yagang Zhang, IntechOpen, DOI: 10.5772/8615. 

Daniela P. Alves, Li Weigang and Bueno B. Souza (January 1st 2008). Reinforcement Learning to Support Meta-Level Control in Air Traffic Management, Reinforcement Learning, Cornelius Weber, Mark Elshaw and Norbert Michael Mayer, IntechOpen, DOI: 10.5772/5293.

Yoshiyuki Tajima and Takehisa Onisawa (February 1st 2010). Model-based Reinforcement Learning with Model Error and Its Application, Application of Machine Learning, Yagang Zhang, IntechOpen, DOI: 10.5772/8607. 

We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an agent into following an outsider&#39;s policy. It is pre-computed, therefore fast inferred, and could thus be usable in a real-time scenario. We show its effectiveness on Atari 2600 games in the novel read-only setting. In this setting, the adversary cannot directly modify the agent&#39;s state - its representation of the environment - but can only attack the agent&#39;s observation - its perception of the environment. Directly modifying the agent&#39;s state would require a write-access to the agent&#39;s inner workings and we argue that this assumption is too strong in realistic settings.

AAMAS 2020

CopyCAT: Taking Control of Neural Policies with Constant Attacks

adversarial exemples

attacks

reinforcement learning

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an agent into following an outsider's policy. It is pre-computed, therefore fast inferred, and could thus be usable in a real-time scenario. We show its effectiveness on Atari 2600 games in the novel read-only setting. In this setting, the adversary cannot directly modify the agent's state - its representation of the environment - but can only attack the agent's observation - its perception of the environment. Directly modifying the agent's state would require a write-access to the agent's inner workings and we argue that this assumption is too strong in realistic settings.

technical paper

Conditional Updates of Answer Set Programming and its Applicationin Explainable Planning

Summer Internship Matching with Funding Constraints

Autonomous Shape Formation and Morphing in a Dynamic Environment by a Swarm of Robots

Explainability in Human-Agent Systems

Computational Methods for Simulating Biased Agents

We call for attention to climate change research as a domain of application for multiagent technologies. The multiagent nature of climate change challenges and successful application of multiagent methods in decentralized power grid systems, market organization, and industrial engineering, could improve our ability to address decarbonization (climate change mitigation) and to deal with some unavoidable consequences of global warming (climate change adaptation). We review major challenges to which the community of multiagent systems can contribute, highlight open research problems and argue for the application of multiagent models and solution concepts in a variety of issues related to this global challenge.


Multiagent Climate Change Research

In this demonstration, we introduce a system that facilitates trading agent competitions. Competitions mirror a Walrasian Exchange Economy. Each agent is endowed with a set of digital assets and preferences over them. Agents then search for sellers of the assets they demand and buyers of the assets they sell. They negotiate one- on-one to arrive at an optimal trade, and if successful, settle their transaction trustlessly on an emulated permissionless blockchain. This system is a precursor to a trading platform for digital assets and crypto-tokens in which agents trade on behalf of their users.


Trading Agent Competition with Autonomous Economic Agents

Multirobot systems for covering environments are increasingly used in applications like cleaning, industrial inspection, patrolling, and precision agriculture. The problem of covering a given environment using multiple robots can be naturally formulated and studied as a multi-Traveling Salesperson Problem (mTSP). In a mTSP, the environment is represented as a graph and the goal is to find tours (starting and ending at the same depot) for the robots in order to visit all the vertices with minimum global cost, namely the length of the longest tour. The mTSP is an NP-hard problem for which several approximation algorithms have been proposed. These algorithms usually assume generic environments, but tighter approximation bounds can be reached focusing on specific environments. In this paper, we address the case of environments composed of sub-parts, called modules, that can be reached from each other only through some linking structures. Examples are multi-floor buildings, in which the modules are the floors and the linking structures are the staircases or the elevators, and floors of large hotels or hospitals, in which the modules are the rooms and the linking structures are the corridors. We focus on linear modular environments, with the modules organized sequentially, presenting an efficient (with polynomial worst-case time complexity) algorithm that finds a solution for the mTSP whose cost is within a bounded distance from the cost of the optimal solution. The main idea of our algorithm is to allocate disjoint "blocks" of adjacent modules to the robots, in such a way that each module is covered by only one robot. We experimentally compare our algorithm against some state-of-the-art algorithms for solving mTSPs in generic environments and show that it is able to provide solutions with lower makespan and spending a computing time several orders of magnitude shorter.

Downloads

Next from AAMAS 2020

Conditional Updates of Answer Set Programming and its Applicationin Explainable Planning

Similar lecture

Snooping Attacks on Deep Reinforcement Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2020

Conditional Updates of Answer Set Programming and its Applicationin Explainable Planning

Similar lecture

Snooping Attacks on Deep Reinforcement Learning

Downloads