Deep Hyperbolic Reinforcement Learning for Continuous Control

Abstract

Integrating hyperbolic representations with Deep Reinforcement Learning (DRL) has recently been proposed as a promising approach for enhancing generalization and sample-efficiency in discrete control tasks. In this work, we extend hyperbolic RL to continuous control by introducing a novel hyperbolic actor-critic model. Empirically, our simple implementation outperforms its Euclidean counterpart, with significant gains on 16/24 tasks from the DeepMind Control Suite with pixel inputs. Notably, in the low-data regime, our method even outperforms several pre-trained unsupervised RL agents. Our findings show that hyperbolic representations provide a valuable inductive bias for continuous control.