DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics


Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors. Learning algorithms add some flexibility with the ability to discover the appropriate behavior given either some demonstrations or a reward to guide its exploration with a reinforcement learning algorithm. Reinforcement learning algorithms rely on the definition of state and action spaces that define reachable behaviors. Their adaptation capability critically depends on the representations of these spaces: small and discrete spaces result in fast learning while large and continuous spaces are challenging and either require a long training period or prevent the robot from converging to an appropriate behavior. Beside the operational cycle of policy execution and the learning cycle, which works at a slower time scale to acquire new policies, we introduce the redescription cycle, a third cycle working at an even slower time scale to generate or adapt the required representations to the robot, its environment and the task. We introduce the challenges raised by this cycle and we present DREAM (Deferred Restructuring of Experience in Autonomous Machines), a developmental cognitive architecture to bootstrap this redescription process stage by stage, build new state representations with appropriate motivations, and transfer the acquired knowledge across domains or tasks or even across robots. We describe results obtained so far with this approach and end up with a discussion of the questions it raises in Neuroscience.
Fichier principal
Vignette du fichier
depot_HAL.pdf (13.54 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02562103 , version 1 (12-05-2020)


  • HAL Id : hal-02562103 , version 1


Stephane Doncieux, Nicolas Bredeche, Léni Kenneth Le Goff, Benoît Girard, Alexandre Coninx, et al.. DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics. 2020. ⟨hal-02562103⟩
219 View
49 Download


Gmail Facebook Twitter LinkedIn More