no code implementations • 29 Aug 2023 • Lucien Tisserand, Frédéric Armetta, Heike Baldauf-Quilliatre, Antoine Bouquin, Salima Hassas, Mathieu Lefort
We explain the methodology we developed for improving the interactions accomplished by an embedded conversational agent, drawing from Conversation Analytic sequential and multimodal analysis.
no code implementations • 19 Sep 2022 • Arthur Aubret, Laetitia Matignon, Salima Hassas
The reinforcement learning (RL) research area is very active, with an important number of new contributions; especially considering the emergent field of deep RL (DRL).
no code implementations • 6 Jun 2021 • Arthur Aubret, Laetitia Matignon, Salima Hassas
The optimal way for a deep reinforcement learning (DRL) agent to explore is to learn a set of skills that achieves a uniform distribution of states.
Hierarchical Reinforcement Learning reinforcement-learning +2
no code implementations • ICML Workshop LifelongML 2020 • Arthur Aubret, Laetitia Matignon, Salima Hassas
Then we show that our approach can scale on more difficult MuJoCo environments in which our agent is able to build a representation of skills which improve over a baseline both transfer learning and exploration when rewards are sparse.
no code implementations • 19 Aug 2019 • Arthur Aubret, Laetitia Matignon, Salima Hassas
In this article, we provide a survey on the role of intrinsic motivation in DRL.
no code implementations • 23 Jul 2019 • Benoit Vuillemin, Lionel Delphin-Poulat, Rozenn Nicol, Laëtitia Matignon, Salima Hassas
This paper presents a new algorithm: TSRuleGrowth, looking for partially-ordered rules over a time series.