Single-Reset Divide & Conquer Imitation Learning

no code implementations • 14 Feb 2024 • Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert

Demonstrations are commonly used to speed up the learning process of Deep Reinforcement Learning algorithms.

Imitation Learning

Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration

1 code implementation • 9 Nov 2022 • Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert

This sequential goal-reaching approach raises a problem of compatibility between successive goals: we need to ensure that the state resulting from reaching a goal is compatible with the achievement of the following goals.

reinforcement-learning Reinforcement Learning (RL)

Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents

1 code implementation • 10 Feb 2022 • Ahmed Akakzia, Olivier Serris, Olivier Sigaud, Cédric Colas

In the quest for autonomous agents learning open-ended repertoires of skills, most works take a Piagetian perspective: learning trajectories are the results of interactions between developmental agents and their physical environment.