Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics

Antonin Raffin (1) , Ashley Hill (1) , René Traoré (1) , Timothée Lesort (1) , Natalia Díaz-Rodríguez (2, 1) , David Filliat (1, 2)

1 U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
2 Flowers - Flowing Epigenetic Robots and Systems

Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. This method encodes all the relevant features, performs on par or better than end-to-end learning with better sample efficiency, and is robust to hyper-parameters change.

Domaines: Apprentissage [cs.LG]

Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez, et al.. Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics. SPiRL 2019 : Workshop on Structure and Priors in Reinforcement Learning at ICLR 2019, May 2019, Nouvelle Orléans, United States. ⟨hal-02285831⟩