Self-Composing Policies for Scalable Continual Reinforcement Learning

Mikel Malagon; Josu Ceberio; Jose A. Lozano

2024 ICML ICML 2024

Self-Composing Policies for Scalable Continual Reinforcement Learning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Mikel Malagon, Josu Ceberio, Jose A. Lozano

Topics

Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Robotics

Keywords

catastrophic forgetting knowledge transfer continual reinforcement learning modular architecture growable neural network scalable

Download PDF