Author Topic: Multi-Agent Systems, Intelligent Decision Support and Bitshares  (Read 1003 times)

0 Members and 1 Guest are viewing this topic.

Offline xeroc

  • Board Moderator
  • Hero Member
  • *****
  • Posts: 12922
  • ChainSquad GmbH
    • View Profile
    • ChainSquad GmbH
  • BitShares: xeroc
  • GitHub: xeroc
Quote
Do you see the wisdom in implementing Multi-Agent Systems and Intelligent Decision Support on top of Bitshares?
ABSOLUTLY!  And currently only BitShares offers a reasonable foundation for that .. IMHO!

Offline luckybit

  • Hero Member
  • *****
  • Posts: 2921
    • View Profile
  • BitShares: Luckybit
Quote
Abstract: Since the 1990s, intelligent agents and multi-agent systems with their known characteristics given by the AI community have been used to intelligently support individual or groups of human users in their business or personal decision-making in a large number and variety of applications in the Internet and Web. The developed frameworks of and systems with agent-based decision support differ in the extent to which they cover the typical phases of human decision-making, the types of decisions to be made, and their effectiveness and efficiency of support. In this respect, recommender systems, automated negotiation systems, matchmaker agents, and virtual user agents or avatars are classical examples to name but a few. On the other hand, semantic web technologies have been used during the past decade for providing better decision support through means of formal ontology-based representation, discovery, integration, and sharing of relevant heterogeneous data, knowledge, and services. Both agents and semantic web have deep and common roots in AI. However, despite the tremendous advances in research and development made in each of both technology domains, the full synergetic potential of agent-based and semantics-empowered decision support in innovative applications in the future Internet remains to be unlocked.
In this talk, I will present and discuss the basic principles, potential and challenges of a single and combined use of agents and semantic technologies for intelligent decision support together with selected showcases from different application domains.
http://vimeo.com/90860817

A brief overview of agents:

An intelligent software agent is like a "bot" which you can tell your goals and have it act on your behalf to accomplish these goals. This "bot" is intelligent because it can sense changes in the environment and adjust it's decisions according to the latest events. So for example the agent could be designated to search for an artist coin which meets some minimum criteria and purchase it at the IPO unless specific events happen to alert the agent that maybe it would not be a profitable deal. To direct your agent you would simply tell your agent your goals and it will pursue them using AI. Multi-Agent Systems are intentional systems where multiple intelligent agents "bots" can transact and communicate among each other to further their individual objectives.

We can and should build Multi-Agent Systems as a layer on top of the Bitshares protocol after Turing complete scripting allows for it. This would also allow for Intelligent Decision Support functionality as described in the Youtube video.

There will be more posts after this to go into details on why Multi-Agent Systems and Intelligent Decision Support functionality are so important. For now check out the videos in the references and discuss the potential if you see any.

Reference
“Agents and Semantics for Human Decision-Making” Dr. Matthias Klusch (ICAART 2014)
http://vimeo.com/90860817

Goal Oriented Search Engine
http://web.media.mit.edu/~lieber/Publications/Goose.pdf

What Would They Think?
A Computational Model of Attitudes
http://web.media.mit.edu/~hugo/publications/papers/IUI2004-wwtt.pdf

Software agent
https://en.wikipedia.org/wiki/Software_agent
https://metaexchange.info | Bitcoin<->Altcoin exchange | Instant | Safe | Low spreads