OpenAI Blog October 26, 2017

Learning a hierarchy

We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing fast solving of tasks requiring thousands of timesteps. Our algorithm, when applied to a set of navigation problems, discovers a set of high-level actions for walking and crawling in different directions, which enables the agent to master new navigation tasks quickly.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at OpenAI Blog.

arXiv Machine Learning

Jul 22

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents

arXiv:2508. 14751v2 Announce Type: replace Abstract: We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces.

By Thomas Carta, Cl\'ement Romac, Loris Gaven, Pierre-Yves Oudeyer, Olivier Sigaud, Sylvain Lamprier

llms agents reinforcement-learning

arXiv AI

Sep 10

Efficient Exploration Is Enough

arXiv:2609.07575v1 Announce Type: cross Abstract: This work introduces an alternative view of efficient exploration and studies its theoretical and empirical implications in the absence of extrinsic...

By Mikel Malag\'on, Jon Vadillo, Josu Ceberio, Michael Bowling, Jose A. Lozano

agents

arXiv AI

Sep 12

Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning

The paper reviews hierarchical reinforcement learning (HRL) as a method for enabling agents to explore, plan, and learn in complex, open-ended environments by uncovering temporal structure in experience streams. It discusses the unclear definition of what makes a structure useful, the benefits of HRL for decision‑making challenges, and its impact on AI agent performance trade‑offs. The authors survey various HRL methods—from online learning to offline datasets and large language model integration—and outline the challenges and suitable domains for temporal structure discovery.

By Martin Klissarov, Akhil Bagaria, Ziyan Luo, George Konidaris, Doina Precup, Marlos C. Machado

llms agents reinforcement-learning

arXiv AI

Jul 22

Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach

arXiv:2602. 03087v2 Announce Type: replace-cross Abstract: Quadruped robots are used for primary searches during the early stages of indoor fires.

By Baixiao Huang, Baiyu Huang, Yu Hou

reinforcement-learning robotics

arXiv AI

Aug 5

Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning

arXiv:2608. 02993v1 Announce Type: new Abstract: (Flat) Reinforcement Learning (RL) agents face significant challenges in environments with sparse rewards that require long-horizon reasoning.

By Subrat Prasad Panda, Blaise Genest, Arvind Easwaran

agents reinforcement-learning

arXiv Machine Learning

Jul 1

Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning

arXiv:2507. 23604v2 Announce Type: replace Abstract: Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity.

By Tommaso Marzi, Cesare Alippi, Andrea Cini

agents reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents

Efficient Exploration Is Enough

Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning

Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach

Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning

Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning