Reinforcement Learning in Hyperbolic Spaces: Models and Experiments
This work addresses the challenge of exploration in unknown environments for RL agents, but it appears incremental as it applies existing RL concepts to hyperbolic spaces without claiming major breakthroughs.
The paper tackles the problem of reinforcement learning in hyperbolic spaces by formalizing five exploration setups as RL problems with hyperbolic action spaces, introducing necessary statistical and dynamical models and implementing algorithms based on this framework.
We examine five setups where an agent (or two agents) seeks to explore unknown environment without any prior information. Although seemingly very different, all of them can be formalized as Reinforcement Learning (RL) problems in hyperbolic spaces. More precisely, it is natural to endow the action spaces with the hyperbolic metric. We introduce statistical and dynamical models necessary for addressing problems of this kind and implement algorithms based on this framework. Throughout the paper we view RL through the lens of the black-box optimization.