For questions related to the discretization of a continuous space (e.g. an action space in reinforcement learning) into a discrete one.
Questions tagged [discretization]
4 questions
2
votes
1 answer
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? Does this depend on the type of ANN?
More…
PeterBe
- 212
- 1
- 11
2
votes
1 answer
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 action (e.g. if you have three possible actions you…
PontrYagin
- 23
- 4
2
votes
0 answers
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?
ddaedalus
- 919
- 1
- 6
- 21
0
votes
1 answer
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 Shaping in Deep Reinforcement Learning,…
kitaird
- 115
- 5