For questions related to the concept of an option in reinforcement learning. An option can be viewed as a generalization of an action. Intuitively, it's a macro-action composed of other actions. Formally, it can be defined as a tuple composed of an initiation set, a policy, and a termination set/condition. This notion of option or macro-action gives rise to hierarchical reinforcement learning and semi-Markov decision processes.
Questions tagged [options]
1 questions
7
votes
1 answer
What are options in reinforcement learning?
According to a lecture (week 10) about Reinforcement Learning [1], the concept of an option allows searching the state space of an agent much faster. The lecture was hard to follow because many new terms were introduced in a short time. For me, theā¦
user11571