Deep Reinforcement Learning for Swarm Systems
Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep multi-agent RL based on mean embeddings of distributions. We treat the agents as samples of a distribution and use the empirical mean embedding as input for a decentralized policy. We define different feature spaces of the mean embedding using histograms, radial basis functions and a neural network learned end-to-end. We evaluate the representation on two well known problems from the swarm literature (rendezvous and pursuit evasion), in a globally and locally observable setup. For the local setup we furthermore introduce simple communication protocols. Of all approaches, the mean embedding representation using neural network features enables the richest information exchange between neighboring agents facilitating the development of more complex collective strategies.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Maximilian Hüttenrauch (add twitter)
Adrian Šošić (add twitter)
Gerhard Neumann (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
Stargazers:
7
Forks:
1
Open Issues:
0
Network:
1
Subscribers:
12
Language:
Python
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
07/19/18 12:45AM
10,712
2,596
Tweets
gubayuhjin: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
GeekOnSteroids: RT @HubBucket: Deep Reinforcement Learning for Swarm Systems. ✨https://t.co/5prCKH5Bhj @HubBucket, @HubBucket360, @HubBucketEP, @HubBucke…
garybartanus: RT @HubBucket: Deep Reinforcement Learning for Swarm Systems. ✨https://t.co/5prCKH5Bhj @HubBucket, @HubBucket360, @HubBucketEP, @HubBucke…
HubBucket: Deep Reinforcement Learning for Swarm Systems. ✨https://t.co/5prCKH5Bhj @HubBucket, @HubBucket360, @HubBucketEP, @HubBucketIND, @HubStackOS, @HubClouds, @HubSparks, @HubXStream, @HubGenomics, @HubBiotech #DataScience, #MachineLearning, #DeepLearning, #NeuralNetworks https://t.co/6YXRnB09fo
Charlot84074713: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
jumpjoe78: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
GeekOnSteroids: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
gaialive: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
DrPjenFI: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
Santiag72427700: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
kx_chg: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
b_cavello: RT @arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
arxiv_org: Deep Reinforcement Learning for Swarm Systems. https://t.co/ukTJOaLlwJ https://t.co/eS2HasnuyF
nmfeeds: [O] https://t.co/9QFZ8Sou2U Deep Reinforcement Learning for Swarm Systems. Recently, deep reinforcement learning (RL) meth...
nmfeeds: [AI] https://t.co/9QFZ8Sou2U Deep Reinforcement Learning for Swarm Systems. Recently, deep reinforcement learning (RL) met...
Images
Related