AI engineering glossary · Reinforcement learning
What is options framework?
Options framework: A formalism for temporally extended actions. An option has a set of situations where it can start, an internal rule for behaving, and a condition for stopping. Options let learners plan over multi-step skills instead of single steps.
Options framework: an example
The option 'open door' starts when near a door, runs several motor steps, and stops once the door is open.
Related terms
- Hierarchical reinforcement learning
- Semi-Markov decision process
- Action
- Policy (reinforcement learning)
More Reinforcement learning terms
- Overestimation bias
- Partially observable Markov decision process
- Policy evaluation
- Policy gradient theorem
- Policy improvement
- Policy iteration
- Potential-based reward shaping
- Prioritised experience replay
Where you learn it
Options framework is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.