Jan Ole Berndt

The Interaction Effort in Autonomous Logistics Processes: Potential and Limitations for Cooperation

Autonomous control in logistics decreases the computational effort for process control by problem decomposition. To this end, decision-making is delegated to the participating logistics entities. The more process control is decentralised the more interaction effort arises for coordinating the participants for efficient resource utilisation. This increase in interaction effort might even outweigh the decrease in computational effort gained by decomposition. Therefore, it is necessary to reduce the interaction effort by adequate organisational structures. Team formation as a prerequisite for establishing these structures, however, also requires interaction effort. Hence, this chapter analytically narrows the optimal degree at which autonomous control is applied by the interaction effort arising for individual and team action as well as team formation.

Efficient Multiagent Coordination in Dynamic Environments

Agent coordination is a fundamental task in designing and operating multiagent systems. However, in dynamically changing environments, coordination must balance proactive and reactive behaviors in order to enable efficient operations while retaining the necessary flexibility to react to unforeseen events. This paper introduces adaptive agent relationships for coping with these contradictory requirements. In this approach, agents dynamically establish relationships which are represented as interaction patterns. On the one hand, these patterns enable efficient coordination by restricting the number of potential interaction flows to those offering the best estimated outcome. On the other hand, they can adapt to environmental changes, as the agents continuously reconsider their relationships in a feedback loop of estimated interaction flows and actually observed coordination outcomes. The paper formalizes the agent decision-making process enabling adaptive relationships and applies it to a logistics network scenario. A comparative evaluation demonstrates its ability to efficiently coordinate agent interaction in a dynamic environment.

Anticipatory Behavior of Software Agents in Self-organizing Negotiations

Software agents are a well-established approach for modeling autonomous entities in distributed artificial intelligence. Iterated negotiations allow for coordinating the activities of multiple autonomous agents by means of repeated interactions. However, if several agents interact concurrently, the participants’ activities can mutually influence each other. This leads to poor coordination results. In this paper, we discuss these interrelations and propose a self-organization approach to cope with that problem. To that end, we apply distributed reinforcement learning as a feedback mechanism to the agents’ decision-making process. This enables the agents to use their experiences from previous activities to anticipate the results of potential future actions. They mutually adapt their behaviors to each other which results in the emergence of social order within the multiagent system. We empirically evaluate the dynamics of that process in a multiagent resource allocation scenario. The results show that the agents successfully anticipate the reactions to their activities in that dynamic and partially observable negotiation environment. This enables them to maximize their payoffs and to drastically outperform non-anticipating agents.

Distributed Reinforcement Learning for Optimizing Resource Allocation in Autonomous Logistics Processes

This paper examines multi-agent coordination for resource allocation tasks in autonomous logistics processes. It identifies requirements for the learning of optimal behavior in a multi-agent setting. Based on a real-world logistics application, the paper distinguishes between single resource allocation by independent agents and joint activities by agent teams. For both cases it introduces adaptations of the Q-learning algorithm and evaluates their convergence as well as their scalability for large scenarios. The results demonstrate that the known conditions for the convergence of multi-agent reinforcement learning are insufficient. This leads to the identification of an additional requirement for convergence in this paper.

Self-Organizing Logistics Process Control: An Agent-Based Approach

Logistics networks face the contradictory requirements of achieving high operational effectiveness and efficiency while retaining the ability to adapt to a changing environment. Changing customer demands and network participants entering or leaving the system cause these dynamics and hamper the collection of information which is necessary for efficient process control. Decentralized approaches representing logistics entities by autonomous artificial agents help coping with these challenges. Coordination of these agents is a fundamental task which has to be addressed in order to enable successful logistics operations. This paper presents a novel approach to self-organization for multiagent system coordination. The approach avoids a priori assumptions regarding agent characteristics by generating expectations solely based on observable behavior. It is formalized, implemented, and applied to a logistics network scenario. An empirical evaluation shows its ability to approximate optimal supply network configurations in logistics agent coordination.

Intentional Forgetting in Artificial Intelligence Systems: Perspectives and Challenges.

Current trends, like digital transformation and ubiquitous computing, yield in massive increase in available data and information. In artificial intelligence (AI) systems, capacity of knowledge bases is limited due to computational complexity of many inference algorithms. Consequently, continuously sampling information and unfiltered storing in knowledge bases does not seem to be a promising or even feasible strategy. In human evolution, learning and forgetting have evolved as advantageous strategies for coping with available information by adding new knowledge to and removing irrelevant information from the human memory. Learning has been adopted in AI systems in various algorithms and applications. Forgetting, however, especially intentional forgetting, has not been sufficiently considered, yet. Thus, the objective of this paper is to discuss intentional forgetting in the context of AI systems as a first step. Starting with the new priority research program on ‘Intentional Forgetting’ (DFG-SPP 1921), definitions and interpretations of intentional forgetting in AI systems from different perspectives (knowledge representation, cognition, ontologies, reasoning, machine learning, self-organization, and distributed AI) are presented and opportunities as well as challenges are derived.

An Agent Architecture for Simulating Communication Dynamics in Social Media

Social media like Facebook, Twitter, or Google+ have become important communication channels. Nonetheless, the distribution and dynamics of that communication make it difficult to analyze and understand. To overcome this, we propose an agent architecture for modeling and simulating user behavior to analyze communication dynamics in social media. Our agent decision-making method utilizes sociological actor types to represent motivations of media users and their impact on communicative behavior. We apply this concept to a simulation of real world Twitter communication accompanying a German television program. Our evaluation shows that the agent architecture is capable of simulating communication dynamics in human media usage.

Towards Simulation-Based Role Optimization in Organizations

The modern workplace is driven by a high amount of available information which can be observed in various domains, e.g., in Industry 4.0. Hence, the question arises: Which competences do actors need to build and efficient work environment? This paper proposes an simulation-based optimization approach to adapt role configurations for team work scenarios. The approach was tested using a multiagent-based job-shop-scheduling model to simulate the effects of various role configurations.