Learning a hierarchy
OpenAI Blog
DeepMind developed a hierarchical reinforcement learning algorithm that learns reusable high-level actions to solve multiple tasks more efficiently. The algorithm enabled agents to master navigation tasks requiring thousands of timesteps by discovering intermediate behaviors like directional walking and crawling. This approach allows new tasks to be solved faster by reusing previously learned high-level action patterns rather than learning from scratch each time.
Why it matters
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.
