Skip to yearly menu bar Skip to main content


Poster

Self-Composing Policies for Scalable Continual Reinforcement Learning

Mikel Malagón · Josu Ceberio · Jose A Lozano

Hall C 4-9 #1105
[ ] [ Project Page ] [ Paper PDF ]
[ Poster
Thu 25 Jul 2:30 a.m. PDT — 4 a.m. PDT
 
Oral presentation: Oral 5D Continuous Learning
Thu 25 Jul 1:30 a.m. PDT — 2:30 a.m. PDT

Abstract:

This work introduces a growable and modular neural network architecture that naturally avoids catastrophic forgetting and interference in continual reinforcement learning. The structure of each module allows the selective combination of previous policies along with its internal policy accelerating the learning process on the current task. Unlike previous growing neural network approaches, we show that the number of parameters of the proposed approach grows linearly with respect to the number of tasks, and does not sacrifice plasticity to scale. Experiments conducted in benchmark continuous control and visual problems reveal that the proposed approach achieves greater knowledge transfer and performance than alternative methods.

Chat is not available.