Author(s): Sherwin Chen

Originally published on Towards AI.

Hindsight experience replay for multi-level hierarchies

the 4-level HAC agent on the inverted pendulum

We discuss a novel Hierarchical Reinforcement Learning(HRL) framework that can efficiently learn multiple levels of policies in parallel. Experiments shows, this framework, proposed by Andrew Levy et al. at ICLR 2019, can significantly accelerate learning in sparse reward problems, specifically those whose objective is to reach some goal state. Noticeably, this is the first framework that succeeds in learning 3-level hierarchies in parallel in tasks with continuous state and action space. Some experiments done by the authors even demonstrate its capability to harness 4-level hierarchies. This video shows its competence in 2- and… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI