Tutorial 1 Session, Day 3: 20th, 15:00-17:00JST

Title of the tutorial: Automated Negotiation in Supply Chain Management Competition

Acronym of the tutorial: SCM

The name and email address of the presenter(s): Yasser Mohammad

The name and email address of the presenter(s):

Principal Researcher, Data Science Research Laboratories, NEC, Japan Visiting Researcher, AIST, RIKEN, Japan

Associate Professor, Assiut University, Egypt y.mohammad@nec.com

Keywords: Automated Negotiation, Machine Learning, NegMAS, Supply Chain Management, ANAC

Duration: 2 hours.

Brief description:

Automated negotiation between intelligent agents is attracting more attention from the research community especially with the wider market penetration of intelligent agents and the need to coordinate their behavior. The International Automated Negotiating Agents Competition (ANAC) provided stimulation for this research since its intro- duction in 2010. Since 2019, a new league was added to ANAC focusing on application of automated negotiation in a realistic business-like Supply Chain Management scenario (SCML). This tutorial will introduce the audience to the SCML and walk them through the development of an agent for the competition highlighting the research challenges involved.

Tutorial Web site: http://yasserm.com/prima-2020-scml-tutorial/

Tentative Detailed outline of the tutorial

The tutorial will consist of two main parts with a 10-min break.

  • Theoretical Session (40min) This part of the tutorial introduces the ANAC competition and the SCML describing the canonical structure of agent decomposition for the competition

  • The negotiation problem (5min) Different definitions of the negotiation problem, negotiation protocol, main differences between negotiations and auctions.

  • ANAC (5min) A short history of the ANAC competition.

  • SCM World (10min) Introduces the game design for SCML.

  • Why SCML (5min) Provides the rationale behind the SCML design.

  • Agent decomposition (15min) Introduces the decomposition of SCML agents into two inter-related components: The trading strategy, negotiation strategy, production strategy, and signing strategy.

  • break (5min)

  • Development Environment (15min) A hands-on installation and configuration tutorial

  • Installing SCML (5min) Goes through the process of installation and configuration for the SCML package with the underlying NegMAS platform and the repository of SCML agents.

  • Running a simulation (5min) Goes through the process of running a single simulation and understanding log files.

  • Running tournaments (5min) Introduces tournaments and their parameters, as well as methods, ensure that com- parisons are fair when running tournaments.

  • break (5min)

  • Live Development of an agent (20min) Provides a hands-on demo for developing an agent for the SCM world.

  • An ML-based trading strategy (10min) Develops a trading strategy that uses ML for predicting various aspects of the SCM world simulation.

  • Putting it all together (10min) Combines the developed trading strategy with built-in components to create a complete agent for SCML

  • Development Example (30min) This final part of the tutorial aims at giving the participants confidence that they could grasp the general structure of an SCML agent and that they can develop an agent for the competition and/or participate in related research in the future. We propose two alternatives here. Depending on the readiness of the participants will either do a hands-on hackathon or a study of existing strategies for the league.

  • Examples of Agent Strategies (30min) This part of the tutorial will walk the participants through the strategies used by some of the finalists in SCML2020 highlighting the different ways for improving upon the builtin agents.

  • Hands-on hackathon (30min) Participants will be given 30min to develop their own agent focusing on modifying a single component of the newly developed agent. The main goal of this step is not to come up with a strong agent but to make sure that the participant has understood the structure of the agent and build confidence in her/his ability to develop a real agent for future competitions.

  • Conclusions (5min) The tutorial will be wrapped-up by a summary of the information introduced in the first session about automatic negotiation and will provide interesting directions of research inviting the audience to actively participating in pushing forward this exciting domain.

Instructor

The presenter is a Principal Researcher at NEC (Data Science Research Laboratories), Japan and an Associate Professor at Assiut University, Egypt. He also holds visiting researcher positions at AIST and RIKEN national research institutes, Japan. He received his Ph.D. from Kyoto University, Japan in 2009 in the area of intelligence science and technology. Recipient of four best paper awards from ICCAS 2012, IEEE/SICE SII 2011, IEA/AIE 2009, and IEA/AIE 2009. Author of Conversational Informatics: A data-intensive approach (Springer, 2015) and Data mining for Social Robotics (Springer, 2016). His research focuses on automatic negotiation, multi-agent systems, and applications of data mining techniques to time-series data. Published over 100 international publications in these areas with an h-index of 16. Co-founder of Ayonix Inc., Japan, and Tebex IT, Egypt, and a senior IEEE member.