Pierre Dangauthier

Learn More
We extend the Bayesian skill rating system TrueSkill to infer entire time series of skills of players by smoothing through time instead of filtering. The skill of each participating player, say, every year is represented by a latent skill variable which is affected by the relevant game outcomes that year, and coupled with the skill variables of the previous(More)
Domestic and real world robotics requires continuous learning of new skills and behaviors to interact with humans. Auto-supervised learning, a compromise between supervised and completely unsupervised learning, consist in relying on previous knowledge to acquire new skills. We propose here to realize auto-supervised learning by exploiting statistical(More)
„his do™ument presents some views on the sem—nti™ of the pro˜—˜ility notionF st9s m—inly — summ—ry of di'erent re—dingsD in p—rti™ul—r of — Stanford Encyclopaedia of Philosophy —rti™leF €ro˜—˜ilities —re d—ily used in re—l world —ppli™—tionD often without — ™le—r underst—nding of their m—them—ti™—l found—tion —nd of the me—ning we —tt—™h to themF „his l—™k(More)
  • 1