A simple metric for turn-taking in emergent communication

Raffensperger, Peter A; Webb, Russell Y.; Bones, Philip J.; McInnes, Allan

doi:10.1177/1059712311421831

Cited by 6 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The desired behaviour must be quantified so that its presence or absence can be measured. For example, turn-taking is quantifiable with the metric developed by Raffensperger et al (2012). 2.…”

Section: Discussionmentioning

confidence: 99%

“…One way to coordinate is to use previously known medium-access control protocols such as ALOHA or Ethernet (Tanenbaum, 2002). However, the collide-and-back-off approach of many medium-access control protocols makes for inefficient use of the channel in high-traffic situations; protocols that have a high turn-taking metric value also fairly maximise channel use among the agents, by the definition of the turn-taking metric (Raffensperger et al, 2012). Perhaps the agents could use their successful messages on the channel to transmit information about when they needed to use the channel.…”

Section: Simulated Medium-access Gamesmentioning

confidence: 99%

“…We use the turn-taking metric that we previously developed (Raffensperger et al, 2012), τ τ ( t , r ) , to measure the quantity of turn-taking present in the results of a particular simulation. Our turn-taking metric assumes that agents are sharing a limited resource; here the interfering communications channel is the shared resource.…”

Section: Simulated Medium-access Gamesmentioning

confidence: 99%

“…Some methods of rewarding the agents result in turn-taking as a system behaviour. We measure the degree of turn-taking using a metric that we previously developed and demonstrated (Raffensperger, Webb, Bones, & McInnes, 2012).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Rewards for pairs of Q-learning agents conducive to turn-taking in medium-access games

et al. 2012

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Simulated Medium-access Gamesmentioning

confidence: 99%

Section: Simulated Medium-access Gamesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Rewards for pairs of Q-learning agents conducive to turn-taking in medium-access games

et al. 2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, turn-taking is a pervasive process in social interaction: turn-taking occurs during any form of communication, where the interlocutors need to take turns in order to successfully understand one another. In fact, turn-taking can be seen as two or more agents sharing a resource that cannot be allocated to more than one agent at any given time [139]. Consequently, even when dealing with primal behaviours such as joint attention, where turn-taking corresponds to the RJA-(EJA)-IJA cycle, tackling this problem is paramount, and mostly an open research question [29], although some principled work has already been carried out to study turn-taking in other, very specific scenarios, such as spoken dialogue generation between robots and humans -see, for example, Raux and Eskenazi [140].…”

Section: Goal Action and Behaviour Selection -Regulating And Learmentioning

confidence: 99%

Attentional Mechanisms for Socially Interactive Robots–A Survey

Ferreira

Dias

2014

IEEE Trans. Auton. Mental Dev.

View full text Add to dashboard Cite

This review intends to provide an overview of the state of the art in the modelling and implementation of automatic attentional mechanisms for socially interactive robots. Humans assess and exhibit intentionality by resorting to multisensory processes that are deeply rooted within low-level automatic attention-related mechanisms of the brain. For robots to engage with humans properly, they should also be equipped with similar capabilities. Joint attention, the precursor of many fundamental types of social interactions, has been an important focus of research in the past decade and a half, therefore providing the perfect backdrop for assessing the current status of stateof-the-art automatic attentional-based solutions. Consequently, we propose to review the influence of these mechanisms in the context of social interaction in cutting-edge research work on joint attention. This will be achieved by summarising the contributions already made in these matters in robotic cognitive systems research, by identifying the main scientific issues to be addressed by these contributions and analysing how successful they have been in this respect, and by consequently drawing conclusions that may suggest a roadmap for future successful research efforts.Index Terms-automatic attentional mechanisms, multisensory active perception, socially interactive robots, joint attention, bottom-up influences, top-down influences, probabilistic, hierarchical/modular architecture This is the author's version of an article that has been published in this journal. Changes were made to this version by the publisher prior to publication.The final version of record is available at http://dx.

show abstract

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

2021

View full text Add to dashboard Cite

We are glad to pen the first few words for the proceedings of SIGDIAL 2021, the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. The SIGDIAL conference is a premier publication venue for research in discourse and dialogue. This year, the conference is organized as a hybrid event with both in-person and virtual participation on July 29-31, 2021, right before ACL-IJCNLP 2021. The 2021 Young Researchers' Roundtable on Spoken Dialog Systems (YRRSDS 2021) is also held as a satellite event. The SIGDIAL 2021 program features three keynote talks, 6 paper presentation sessions, 1 demo session, and 2 special sessions, entitled "Summarization of Dialogues and Multi-Party Meetings", and "Safety for E2E Conversational AI".COVID has changed the way we work, but it doesn't hamper our research progress. We received 142 submissions this year, comprising 88 long papers, 49 short papers, and 5 demo descriptions. We had 12 Senior Program Committee (SPC) members who were each responsible for 11-12 papers, leading the discussion process and also contributing meta-reviews. Each submission was assigned to an SPC member and received at least three reviews. Decisions carefully considered the original reviews, meta-reviews, and discussions among reviewers facilitated by the SPCs. We are immensely grateful to the members of the Program Committee and Senior Program Committee for efforts in providing excellent, thoughtful reviews of the large number of submissions. Their contributions have been essential to selecting the accepted papers and providing a high-quality technical program for the conference. We have aimed to develop a broad, varied program spanning the many positively rated papers identified by the review process. We accepted 59 papers in total: 40 long papers (45%), 15 short papers (31%), and 4 demo descriptions, for an overall acceptance rate of 41.5%, in line with prior years. One keynote will highlight each of the three days of the conference. In organizing this hybrid inperson/virtual conference, we have tried to maintain as much of the spirit of a fully online conference as possible. Recordings for all papers and demos have been made available several days before the start of the conference, for participants to watch asynchronously. Long and short papers are organized into sessions taking into consideration the presenters' time zones. Regular papers sessions span 8-11 papers, each presented as a two-minute pre-recorded talk followed by five minutes of live Q&A. For demos, we organized four parallel zoom rooms to allow participants to interact with and observe live interactions with the systems. The topics represent the breadth of research in discourse and dialogue. A conference of this size requires the energy, guidance, and contributions of many parties, and we would like to take this opportunity to thank and acknowledge them all. We thank our three keynote speakers, Julia Hirschberg (Columbia University), Raymond J. Mooney (University of Texas at Austin), and Jason Weston (Facebook AI & NYU), for...

show abstract

A simple metric for turn-taking in emergent communication

Cited by 6 publications

References 39 publications

Rewards for pairs of Q-learning agents conducive to turn-taking in medium-access games

Rewards for pairs of Q-learning agents conducive to turn-taking in medium-access games

Attentional Mechanisms for Socially Interactive Robots–A Survey

Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue

Contact Info

Product

Resources

About