RoboCup: The Robot World Cup Initiative
AGENTS '97 Proceedings of the first international conference on Autonomous agents
Multiagent learning using a variable learning rate
Artificial Intelligence
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Computer Networks
Evolving Communication without Dedicated Communication Channels
ECAL '01 Proceedings of the 6th European Conference on Advances in Artificial Life
Cooperation and coordination in the turn-taking dilemma
Proceedings of the 9th conference on Theoretical aspects of rationality and knowledge
Nash q-learning for general-sum stochastic games
The Journal of Machine Learning Research
Adaptability and diversity in simulated turn-taking behavior
Artificial Life
An introduction to ROC analysis
Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Agendas for multi-agent learning
Artificial Intelligence
Learning to communicate in a decentralized environment
Autonomous Agents and Multi-Agent Systems
A leader-follower turn-taking model incorporating beat detection in musical human-robot interaction
Proceedings of the 4th ACM/IEEE international conference on Human robot interaction
Optimizing endpointing thresholds using dialogue features in a spoken dialogue system
SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue
Random access game and medium access control design
IEEE/ACM Transactions on Networking (TON)
A simple metric for turn-taking in emergent communication
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
A Comprehensive Survey of Multiagent Reinforcement Learning
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Hi-index | 0.00 |
We describe a class of stateful games, which we call 'medium-access games', as a model for human and machine communication and demonstrate how to use the Nash equilibria of those games as played by pairs of agents with stationary policies to predict turn-taking behaviour in Q-learning agents based on the agents' reward function. We identify which fixed policies exhibit turn-taking behaviour in medium-access games and show how to compute the Nash equilibria of such games by using Markov chain methods to calculate the agents' expected rewards for different stationary policies. We present simulation results for an extensive range of reward functions for pairs of Q-learners playing medium-access games and we use our analysis for stationary agents to develop predictors for the emergence of turn-taking. We explain how to use our predictors to design reward functions for pairs of Q-learning agents that are conducive (or prohibitive) to the emergence of turn-taking in medium-access games. We focus on designing multi-agent reinforcement learning systems that deliberately produce coordinated turn-taking but we also intend our results to be useful for analysing emergent turn-taking behaviour. Based on our turn-taking related results, we suggest ways to use our methodology to designs rewards for quantifiable behaviours besides turn-taking.