Skip to main content

Questions tagged [transition-model]

For questions related to the transition model of a Markov decision process or other Markov models. This term is often used in reinforcement learning (RL) to distinguish between model-based and model-free RL algorithms, where model-based algorithms use the transition model while model-free don't use it.

Filter by
Sorted by
Tagged with
1 vote
1 answer

How do you generate the transition probabilities of a non-trivial MDP?

I understand an MDP (Markov Decision Process) model is a tuple of $\{S, A, P, R \}$ where: $S$ is a discrete set of states $A$ is a discrete set of actions $P$ is the transition matrix ie. $P(s' \mid ...
Brendan Hill's user avatar