2022 Developer Survey is open! Take survey.

Questions tagged [discretization]

For questions related to the discretization of a continuous space (e.g. an action space in reinforcement learning) into a discrete one.

Filter by
Sorted by
Tagged with
0 votes
1 answer
62 views

When should discretization of observations be considered?

I found some literature regarding the design of action-spaces and that e.g. a discretization of continuous actions in video-game environments can be crucial for successful learning (Action Space ...
user avatar
  • 85
2 votes
1 answer
359 views

Can neural networks have continuous inputs and outputs, or do they have to be discrete?

In general, can ANNs have continuous inputs and outputs, or do they have to be discrete? So, basically, I would like to have a mapping of continuous inputs to continuous outputs. Is this possible? ...
user avatar
  • 213
2 votes
1 answer
458 views

What should the input and output of the Q-network be in the case of an ordinal action space?

I recently started looking into implementations of the DQN algorithm (e.g. TensorFlow) in some more detail. All the implementations that I found use a network that gives an output for each possible ...
user avatar
2 votes
0 answers
51 views

When to do discretization to decrease the state/action space in RL?

When to do discretization to decrease the state/action space in RL? Can you give me some references that such a technique is used?
user avatar
  • 879