Improving alignment of dialogue agents via targeted human judgements.
Amelia GlaeseNat McAleeseMaja TrebaczJohn AslanidesVlad FiroiuTimo EwaldsMaribeth RauhLaura WeidingerMartin ChadwickPhoebe ThackerLucy Campbell-GillinghamJonathan UesatoPo-Sen HuangRamona ComanescuFan YangAbigail SeeSumanth DathathriRory GreigCharlie ChenDoug FritzJaume Sanchez EliasRichard GreenSona MokráNicholas FernandoBoxi WuRachel FoleySusannah YoungIason GabrielWilliam IsaacJohn MellorDemis HassabisKoray KavukcuogluLisa Anne HendricksGeoffrey IrvingPublished in: CoRR (2022)
Keyphrases
- artificial agents
- multi agent
- multi agent systems
- human computer
- human machine
- human communication
- multiagent systems
- cooperative
- dialogue system
- agent systems
- multiple agents
- conversational agents
- intelligent agents
- autonomous agents
- agent teams
- software agents
- agent interactions
- dialogue games
- dialogue management
- personality types
- human users
- multi party
- dynamic environments
- tutorial dialogue
- virtual agents
- virtual characters
- mobile agents
- man machine
- bounded rationality
- dynamic time warping
- trust model
- action selection
- communicative acts
- human behavior
- turn taking
- mixed initiative
- interacting agents
- agent architecture
- speech acts
- agent technology
- personality traits
- social welfare
- learning agents
- coalition formation
- agent model