Learning a hierarchy

📰 OpenAI News

OpenAI develops a hierarchical reinforcement learning algorithm for efficient task solving

advanced Published 26 Oct 2017
Action Steps
  1. Apply hierarchical reinforcement learning to navigation problems
  2. Discover high-level actions for walking and crawling in different directions
  3. Use the learned actions to master new navigation tasks quickly
  4. Experiment with the algorithm on various tasks requiring thousands of timesteps
Who Needs to Know This

AI engineers and researchers can leverage this algorithm to improve agent performance in complex tasks, while product managers can apply it to develop more efficient AI-powered products

Key Insight

💡 Hierarchical reinforcement learning can learn high-level actions useful for solving a range of tasks

Share This
🤖 New hierarchical RL algorithm enables fast task solving!

Key Takeaways

OpenAI develops a hierarchical reinforcement learning algorithm for efficient task solving

Full Article

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.
Read full article → ← Back to Reads