Salima Hassas

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). However a number of scientific and technical challenges still need to be resolved, amongst which we can mention the ability to abstract actions or the difficulty to explore the environment in sparse-reward settings which can be addressed by intrinsic motivation (IM). We propose to survey these research works through a new taxonomy based on information theory: we computationally revisit the notions of surprise, novelty and skill learning. This allows us to identify advantages and disadvantages of methods and exhibit current outlooks of research. Our analysis suggests that novelty and surprise can assist the building of a hierarchy of transferable skills that further abstracts the environment and makes the exploration process more robust.

Lucien Tisserand, Frédéric Armetta, Heike Baldauf-Quilliatre et al.

We explain the methodology we developed for improving the interactions accomplished by an embedded conversational agent, drawing from Conversation Analytic sequential and multimodal analysis. The use case is a Pepper robot that is expected to inform and orient users in a library. In order to propose and learn better interactive schema, we are creating a corpus of naturally-occurring interactions that will be made available to the community. To do so, we propose an annotation practice based on some theoretical underpinnings about the use of language and multimodal resources in human-robot interaction. CCS CONCEPTS $\bullet$ Computing methodologies $\rightarrow$ Discourse, dialogue and pragmatics; $\bullet$ Human-centered computing $\rightarrow$ Text input; HCI theory, concepts and models; Field studies.

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. Following this,we introduce DisTop, a new model that simultaneously learns diverse skills and focuses on improving rewarding skills. DisTop progressively builds a discrete topology of the environment using an unsupervised contrastive loss, a growing network and a goal-conditioned policy. Using this topology, a state-independent hierarchical policy can select where the agent has to keep discovering skills in the state space. In turn, the newly visited states allows an improved learnt representation and the learning loop continues. Our experiments emphasize that DisTop is agnostic to the ground state representation and that the agent can discover the topology of its environment whether the states are high-dimensional binary data, images, or proprioceptive inputs. We demonstrate that this paradigm is competitiveon MuJoCo benchmarks with state-of-the-art algorithms on both single-task dense rewards and diverse skill discovery. By combining these two aspects, we showthat DisTop achieves state-of-the-art performance in comparison with hierarchical reinforcement learning (HRL) when rewards are sparse. We believe DisTop opens new perspectives by showing that bottom-up skill discovery combined with representation learning can unlock the exploration challenge in DRL.

Arthur Aubret, Laetitia Matignon, Salima Hassas

Taking inspiration from developmental learning, we present a novel reinforcement learning architecture which hierarchically learns and represents self-generated skills in an end-to-end way. With this architecture, an agent focuses only on task-rewarded skills while keeping the learning process of skills bottom-up. This bottom-up approach allows to learn skills that 1- are transferable across tasks, 2- improves exploration when rewards are sparse. To do so, we combine a previously defined mutual information objective with a novel curriculum learning algorithm, creating an unlimited and explorable tree of skills. We test our agent on simple gridworld environments to understand and visualize how the agent distinguishes between its skills. 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.

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). However a number of scientific and technical challenges still need to be addressed, amongst which we can mention the ability to abstract actions or the difficulty to explore the environment which can be addressed by intrinsic motivation (IM). In this article, we provide a survey on the role of intrinsic motivation in DRL. We categorize the different kinds of intrinsic motivations and detail for each category, its advantages and limitations with respect to the mentioned challenges. Additionnally, we conduct an in-depth investigation of substantial current research questions, that are currently under study or not addressed at all in the considered research area of DRL. We choose to survey these research works, from the perspective of learning how to achieve tasks. We suggest then, that solving current challenges could lead to a larger developmental architecture which may tackle most of the tasks. We describe this developmental architecture on the basis of several building blocks composed of a RL algorithm and an IM module compressing information.

Benoit Vuillemin, Lionel Delphin-Poulat, Rozenn Nicol et al.

This paper presents a new algorithm: TSRuleGrowth, looking for partially-ordered rules over a time series. This algorithm takes principles from the state of the art of rule mining and applies them to time series via a new notion of support. We apply this algorithm to real data from a connected environment, which extract user habits through different connected objects.