Senior Research Scientist, Knowledge Science Research Laboratories, NEC Corporation · Professor, Assiut University

Yasser Mohammad

AI for automated negotiation, multiagent systems, robotics & HRI, machine learning, and time-series analysis.

Explore the research CV (PDF)

Bilateral bargaining Agent AAgent B

Two agents exchange offers along the utility frontier, converging on a Pareto-optimal agreement.

Four threads

Research

Full research statement →

Automated Negotiation

Data-driven and RL-based negotiating agents, negotiation protocols, and the ANAC/SCML competitions that stress-test them.

NegMAS · SCML · ANAC

Multiagent Systems

Coordination and contracting in supply chains and markets, and the simulation worlds where many agents interact under scarce information.

Supply-chain worlds & markets

Robotics & HRI

Embodied interaction and human–robot teaming — the roots of my PhD work on how machines read and respond to people.

Embodied interaction

ML & Time-Series

Pattern discovery and motif mining in sequential data — tools built for interaction logs, now used across negotiation and sensor streams.

Motif discovery · mining

Welcome!

I am a Senior Research Scientist at the Knowledge Science Research Laboratories, NEC, Japan, and a Professor at Assiut University, Egypt.

My research interests span the areas of artificial intelligence applied to automated negotiation, robotics, HRI, multiagent systems, machine learning, and time series analysis.

I worked in academia, small startups, research companies, and research institutes collaborating with engineers, psychologists, and mathematicians.

Since 2010, I taught at all levels from freshmen courses to advanced PhD level courses in computer science, informatics, applied mathematics, software engineering, mechatronics, and robotics.

And, I am still learning …

Selected Publications

Automated Negotiation

Mohammad, Y. (2026). Automated Negotiation with No Information about Partner Utility Functions Using the Tentative Acceptance Unique Offers Protocol. Autonomous Agents and Multi-Agent Systems, 40(1), 21.

@article{mohammad2026tau,
  keywords = {journal, important},
  focus = {negotiation},
  author = {Mohammad, Yasser},
  title = {Automated Negotiation with No Information about Partner Utility Functions Using the Tentative Acceptance Unique Offers Protocol},
  journal = {Autonomous Agents and Multi-Agent Systems},
  volume = {40},
  number = {1},
  pages = {21},
  year = {2026},
  doi = {10.1007/s10458-026-09745-9}
}

With the widespread adoption of AI in industrial and business operations, finding methods to reach agreement between intelligent agents representing self-interested entities in a general-sum environment (cooperation within competition) is attracting more interest in the research community. Negotiation is a common process for reaching agreements between people and human institutions. Automated negotiation is thus being considered for cooperation within competition situations involving AIs. The most widely used protocols for automated negotiation are the Stacked Alternating Offers Protocol (SAOP) for multilateral negotiations and the Alternating Offers Protocol (AOP) for bilateral negotiations which directly model bargaining as in human marketplaces. Several strategies have been proposed for these protocols over the years. In this paper, we propose a modification of the AOP and SAOP protocols and a method for adapting negotiation strategies to the new protocol. We show empirically that the proposed approach leads to higher expected advantage for all agents, and achieves higher agreement rate, higher welfare, and fairer agreements faster. This is achieved at the expense of a small increase in information revelation.

Automated Negotiation

Mohammad, Y. (2023). Optimal Time-Based Strategy for Automated Negotiation. Applied Intelligence, 53(6), 6710–6735.

@article{mohammad2023optimaltime,
  keywords = {journal, important},
  focus = {negotiation},
  author = {Mohammad, Yasser},
  title = {Optimal Time-Based Strategy for Automated Negotiation},
  journal = {Applied Intelligence},
  volume = {53},
  number = {6},
  pages = {6710--6735},
  year = {2023},
  doi = {10.1007/s10489-022-03662-6}
}

Recent years are showing increased adoption of AI technology to automate business and production processes thanks to the recent successes of machine learning techniques. This leads to increased interest in automated negotiation as a method for achieving win-win agreements among self-interested agents. Research in automated negotiation can be traced back to the Nash bargaining game in the mid 20 th century. Nevertheless, finding an optimal negotiation strategy against an unknown opponent with an unknown utility function is still an open area of research. The most recent result in this area is the Greedy Concession Algorithm (GCA) which can be shown to be optimal under specific constraints on both the negotiation protocol (non-repeating offers), opponent (static acceptance-model) and search space (deterministic time-based strategies). In this paper, we extend this line of work by providing an algorithmically faster version of GCA called Quick GCA which reduces the time-complexity of the search process from O(  2 ) to O( ) where is the size of the outcome-space and is the number of negotiation rounds allowed. Moreover, we show that GCA/QGCA can be applied in a more general setting; Namely with repeating-offers protocols and to search the more general probabilistic time-based strategies. Finally, we heuristically extend QGCA to more general opponents with general time-dependent acceptance-model and negotiation settings (real-time limited negotiations) in three steps called , , and that iteratively and greedily modify the policy proposed by applied to an approximate static acceptance model . The paper evaluates the proposed approach empirically against state of the art negotiation strategies (winners of all relevant ANAC competition winners) and shows that it outperforms them in a wide variety of negotiation scenarios.

Automated Negotiation

Mohammad, Y., & Nakadai, S. (2022). Concurrent Negotiations with Global Utility Functions. Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022), 1947–1949. https://www.ifaamas.org/Proceedings/aamas2022/pdfs/p1947.pdf

@inproceedings{mohammad2022concurrentglobal,
  keywords = {conference, important},
  focus = {negotiation},
  author = {Mohammad, Yasser and Nakadai, Shinji},
  title = {Concurrent Negotiations with Global Utility Functions},
  booktitle = {Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022)},
  pages = {1947--1949},
  publisher = {IFAAMAS},
  address = {Auckland, New Zealand},
  year = {2022},
  doi = {10.5555/3535850.3536162},
  url = {https://www.ifaamas.org/Proceedings/aamas2022/pdfs/p1947.pdf}
}

Automated Negotiation is attracting more attention from researchers recently as it is becoming more relevant to industrial and business applications with increased reliance on automated systems. Most research in this area assumes either a single negotiation thread with a well-defined utility function for each agent involved or a set of concurrent negotiations with an ordering of outcomes in each local negotiation. In this paper, we consider an agent engaged in a set of concurrent negotiations with a utility function defined only for the in of them and no locally defined ordering of outcomes in any negotiation independent from what happens in the others. We argue that this problem setting is interesting both from the academic and the industrial points of view. The paper then presents an algorithm that allows such agent to maximize its expected global utility by orchestrating its behavior in all negotiation threads. The performance of the proposed method is analyzed theoretically and empirically using simulation.

Automated Negotiation

Sengupta, A., Mohammad, Y., & Nakadai, S. (2021). An Autonomous Negotiating Agent Framework with Reinforcement Learning Based Strategies and Adaptive Strategy Switching Mechanism. Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), 1163–1172. https://ifaamas.org/Proceedings/aamas2021/pdfs/p1163.pdf

@inproceedings{sengupta2021autonomous,
  keywords = {conference, important},
  focus = {negotiation},
  author = {Sengupta, Ayan and Mohammad, Yasser and Nakadai, Shinji},
  title = {An Autonomous Negotiating Agent Framework with Reinforcement Learning Based Strategies and Adaptive Strategy Switching Mechanism},
  booktitle = {Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021)},
  pages = {1163--1172},
  publisher = {ACM},
  year = {2021},
  doi = {10.5555/3463952.3464087},
  url = {https://ifaamas.org/Proceedings/aamas2021/pdfs/p1163.pdf}
}

Despite abundant negotiation strategies in literature, the complexity of automated negotiation forbids a single strategy from being dominant against all others in different negotiation scenarios. To overcome this, one approach is to use mixture of experts, but at the same time one problem of this method is the selection of experts, as this approach is limited by the competency of the experts selected. Another problem with most negotiation strategies is their incapability of adapting to dynamic variation of the opponent’s behaviour within a single negotiation session resulting in poor performance. This work focuses on both, solving the problem of expert selection and adapting to the opponent’s behaviour with our Autonomous Negotiating Agent Framework. This framework allows real-time classification of opponent’s behaviour and provides a mechanism to select, switch or combine strategies within a single negotiation session. Additionally, our framework has a reviewer component which enables self-enhancement capability by deciding to include new strategies or replace old ones with better strategies periodically. We demonstrate an instance of our framework by implementing maximum entropy reinforcement learning based strategies with a deep learning based opponent classifier. Finally, we evaluate the performance of our agent against state-of-the-art negotiators under varied negotiation scenarios.

Robotics & HRI

Mohammad, Y. F. O., & Nishida, T. (2010). Learning Interaction Protocols Using Augmented Bayesian Networks Applied to Guided Navigation. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), 4119–4126.

@inproceedings{mohammad2010augmentedbayes,
  keywords = {conference, important},
  focus = {robotics},
  author = {Mohammad, Yasser F. O. and Nishida, Toyoaki},
  title = {Learning Interaction Protocols Using Augmented Bayesian Networks Applied to Guided Navigation},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010)},
  pages = {4119--4126},
  publisher = {IEEE},
  address = {Taipei, Taiwan},
  year = {2010},
  doi = {10.1109/IROS.2010.5651719}
}

Research in robot navigation usually concentrates on implementing navigation algorithms that allow the robot to navigate without human aid. In many real world situations, it is desirable that the robot is able to understand natural gestures from its user or partner and use this understanding to guide its navigation. Some algorithms already exist for learning natural gestures and/or their associated actions but most of these systems does not allow the robot to automatically generate the associated controller that allows it to actually navigate in the real environment. Furthermore, a technique is needed to combine the gestures/actions learned from interacting with multiple users or partners. This paper resolves these two issues and provides a complete system that allows the robot to learn interaction protocols and act upon them using only unsupervised learning techniques and enables it to combine the protocols learned from multiple users/partners. The proposed approach is general and can be applied to other interactive tasks as well. This paper also provides a real world experiment involving 18 subjects and 72 sessions that supports the ability of the proposed system to learn the needed gestures and to improve its knowledge of different gestures and their associations to actions over time.

ML & Time-Series

Mohammad, Y. F. O., & Nishida, T. (2010). Mining Causal Relationships in Multidimensional Time Series. In E. Szczerbicki & N. T. Nguyen (Eds.), Smart Information and Knowledge Management: Advances, Challenges, and Critical Issues (Vol. 260, pp. 309–338). Springer.

@incollection{mohammad2010miningcausal,
  keywords = {bookchapter, important},
  focus = {timeseries},
  author = {Mohammad, Yasser F. O. and Nishida, Toyoaki},
  title = {Mining Causal Relationships in Multidimensional Time Series},
  booktitle = {Smart Information and Knowledge Management: Advances, Challenges, and Critical Issues},
  editor = {Szczerbicki, Edward and Nguyen, Ngoc Thanh},
  series = {Studies in Computational Intelligence},
  volume = {260},
  pages = {309--338},
  publisher = {Springer},
  year = {2010},
  doi = {10.1007/978-3-642-04584-4_14}
}

Time series are ubiquitous in all domains of human endeavor. They are generated, stored, and manipulated during any kind of activity. The goal of this chapter is to introduce a novel approach to mine multidimensional time-series data for causal relationships. The main feature of the proposed system is supporting discovery of causal relations based on automatically discovered recurring patterns in the input time series. This is achieved by integrating a variety of data mining techniques. The main insight of the proposed system is that causal relations can be found more easily and robustly by analyzing meaningful events in the time series rather than by analyzing the time series numerical values directly. The RSST (Robust Singular Spectrum Transform) algorithm is used to find interesting points in every time series that is further analyzed by a constrained motif discovery algorithm (if needed) to learn basic events of the time series. The Granger-causality test is extended and applied to the multidimensional time-series describing the occurrences of these basic events rather than to the raw time-series data. The combined algorithm is evaluated using both synthetic and real world data. The real world application is to mine records of activities during a human-robot interaction experiment in which a human subject is guiding a robot to navigate using free hand gesture. The results show that the combined system can provide causality graphs representing the underlying relations between the human’s actions and robot behavior that cannot be recovered using standard causal graph learning procedures. Mining Time Series, Robust Singular Spectrum Transform, Granger-Causality, Mining Causal Relations

ML & Time-Series

Mohammad, Y. F. O., & Nishida, T. (2009). Constrained Motif Discovery in Time Series. New Generation Computing, 27(4), 319–346.

@article{mohammad2009constrainedmotif,
  keywords = {journal, important},
  focus = {timeseries},
  author = {Mohammad, Yasser F. O. and Nishida, Toyoaki},
  title = {Constrained Motif Discovery in Time Series},
  journal = {New Generation Computing},
  volume = {27},
  number = {4},
  pages = {319--346},
  year = {2009},
  doi = {10.1007/s00354-009-0068-x}
}

The goal of motif discovery algorithms is to efficiently find unknown recurring patterns. In this paper we focus on motif discovery in time series. Most available algorithms cannot utilize domain knowledge in any way which results in quadratic or at least super-linear time and space complexity. In this paper we define the Constrained Motif Discovery problem which enables utilization of domain knowledge into the motif discovery process. The paper then provides two algorithms called MCFull and MCInc for efficiently solving the constrained motif discovery problem. We also show that most unconstrained motif discovery problems be converted into constrained ones using a change-point detection algorithm. A novel change-point detection algorithm called the Robust Singular Spectrum Transform (RSST) is then introduced and compared to traditional Singular Spectrum Transform using synthetic and real-world data sets. The results show that RSST achieves higher specificity and is more adequate for finding constraints to convert unconstrained motif discovery problems to constrained ones that can be solved using MCFull and MCInc. We then compare the combination of RSST and MCFull or MCInc with two state-of-the-art motif discovery algorithms on a large set of synthetic time series. The results show that the proposed algorithms provided four to ten folds increase in speed compared the unconstrained motif discovery algorithms studied without any loss of accuracy. RSST+MCFull is then used in a real world human-robot interaction experiment to enable the robot to learn free hand gestures, actions, and their associations by humans and other robots interacting.

Robotics & HRI

Mohammad, Y. F. O., Nishida, T., & Okada, S. (2009). Unsupervised Simultaneous Learning of Gestures, Actions and Their Associations for Human-Robot Interaction. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009), 2537–2544.

@inproceedings{mohammad2009simultaneous,
  keywords = {conference, important},
  focus = {robotics},
  author = {Mohammad, Yasser F. O. and Nishida, Toyoaki and Okada, Shogo},
  title = {Unsupervised Simultaneous Learning of Gestures, Actions and Their Associations for Human-Robot Interaction},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)},
  pages = {2537--2544},
  publisher = {IEEE},
  address = {St. Louis, MO, USA},
  year = {2009},
  doi = {10.1109/IROS.2009.5353987}
}

To enable free natural communication between a human operator and a robot three problems must be faced: Firstly the robot have to know the actions it can do in the world. Secondly the robot must be able to learn the patterns in the perceived behavior of its operator that correspond to commands. Finally the robot needs to know when to execute a specific action based on its perception of the operator’s behavior. In this paper we are interested in free hand gestures as the commanding channel. The most restrictive solution to the aforementioned three problems is to fix the action space (pre-programmed actions), fix the command space (predefined gestures), and fix action-command relation (fixed gesture meanings).Learning by demonstration can be viewed as a technique to relax the first restriction by learning the action space. Gesture interpretation can be viewed as a technique to relax the second restriction by learning the command space. Reinforcement learning can be viewed as a technique for relaxing the third restriction by learning action-command associations (policy). In this paper we propose a novel technique that allows the robot to solve these three problems together learning the action space, the command space, and their relations by just another robot operated by a human operator. The main technical contribution of this paper is the introduction of a novel algorithm that allows the robot to segment and discover patterns in its perceived signals without any prior knowledge of the number of different patterns, their occurrences or lengths. The second contribution is using a Ganger-Causality based test to limit the search space for actions and commands utilizing their relations and taking into account the autonomy level of the robot. The paper also presents a feasibility study in which the learning robot was able to predict actor’s behavior with 95.2 after monitoring a single interaction between a novice operator and a WOZ operated robot representing the actor.

Open source

Software people build on

All projects →

NegMAS

A Python library for building and running situated automated negotiations — the backbone of the ANAC negotiation competitions.

pip install negmasPython

SCML

The Supply Chain Management League: a simulation world where agents negotiate contracts along a production pipeline.

ANAC-SCML trackPython

Education

Background

(2009) Ph.D. Informatics, Kyoto University
(2005) M.S. Computers and Systems, Assiut University
(1998) B.En. Electrical Engineering, Assiut University

Recent

News

2025/03/03

I am giving a tutorial about Reinforcement Learning for Automated Negotiation at AAMAS 2025, Detroit on May 19th, 2025

2025/01/29

I am giving a talk about the integration of automated negotiation, digital twins and data spaces in the Digital Twin Consortium Event in Heilbronn.

2024/10/11

I am giving a talk at the workshop on Fusion of machine learning and mathematical models and deepening theory II about automated negotiation in business applications.

2024/09/11

I am giving a talk at the Digital Twin Consortium about Digital Twin Autonomous Orchestration and Coordination.

All news →

Upcoming

Events

All events →

Yasser Mohammad

Research

Automated Negotiation

Multiagent Systems

Robotics & HRI

ML & Time-Series

Welcome!

Selected Publications

Software people build on

Background

News

Events

About

Contact

Coordinates