Daniel Kudenko

Learn More
We report on an investigation of reinforcement learning techniques for the learning of coordination in cooperative multi-agent systems. Specifically, we focus on a novel action selection strategy for Q-learning (Watkins 1989). The new technique is applicable to scenarios where mutual observation of actions is not possible.To date, reinforcement learning(More)
and the AgentLink Community. This document may be copied and redistributed provided that all copies are complete and preserve this notice. Multiple copying for instructional purposes is permitted but should be notified to admin@agentlink.org Neither the editors, authors, contributors, reviewers nor supporters accept any responsibility for loss or damage(More)
Reinforcement learning, while being a highly popular learning technique for agents and multi-agent systems, has so far encountered difficulties when applying it to more complex domains due to scaling-up problems. This paper focuses on the use of domain knowledge to improve the convergence speed and optimality of various RL techniques. Specifically, we(More)
The family of terminological representation systems has its roots in the representation system kl-one. Since the development of this system more than a dozen similar representation systems have been developed by various research groups. These systems vary along a number of dimensions. In this paper, we present the results of an empirical analysis of six(More)
In recent years, multi-agent systems (MAS) have received increasing attention in the artificial intelligence community. Research in multi-agent systems involves the investigation for autonomous, rational and flexible behavior of entities such as software programs or robots, and their interaction and coordination in such diverse areas as robotics (Kitano et(More)
We report on an investigation of reinforcement learning techniques for the learning of coordination in cooperative multiagent systems. These techniques are variants of Q-learning (Watkins, 1989) that are applicable to scenarios where mutual observation of actions is not possible. To date, reinforcement learning approaches for such independent agents did not(More)
Potential-based reward shaping has previously been proven to both be equivalent to Q-table initialisation and guarantee policy invariance in single-agent reinforcement learning. The method has since been used in multi-agent reinforcement learning without consideration of whether the theoretical equivalence and guarantees hold. This paper extends the(More)
Organisations are increasingly recognising the importance of managing what they consider their most valuable asset: knowledge. This work is a contribution towards that end, proposing a system for representing, recording, using, retrieving, and managing individual and group knowledge: a group memory system. This paper describes the high-level objective of(More)
In this paper we present a system which automatically generates interactive stories that are focused around dilemmas to create dramatic tension. A story designer provides the background of the story world, such as information on characters and their relations, objects, and actions. In addition, our system is provided with knowledge of generic story actions(More)