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 will have three output units in your network). This makes a lot of sense from a computational standpoint and seems to work fine if you are dealing with categorical action spaces (e.g "left" or "right").

However, I am currently working with an action space that I discretized and the actions have an ordinal meaning (e.g. you can drive left or right in 5 degree increments). I assume that the action-value function has some monotonicity in the action component (think driving 45 degree to the left instead of 40 will have similar value). Am I losing information on the similarity of actions, if I use a network that has an output unit for each possible action? Are there implementations of the DQN available in which actions are used as network inputs?

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 will have three output units in your network). This makes a lot of sense from a computational standpoint and seems to work fine if you are dealing with categorical action spaces (e.g "left" or "right").

However, I am currently working with an action space that I discretized and the actions have an ordinal meaning (e.g. you can drive left or right in 5-degree increments). I assume that the action-value function has some monotonicity in the action component (think driving 45 degrees to the left instead of 40 will have a similar value). 

Am I losing information on the similarity of actions, if I use a network that has an output unit for each possible action? 

Are there implementations of the DQN available in which actions are used as network inputs?

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 will have three output units in your network). This makes a lot of sense from a computational standpoint and seems to work fine if you are dealing with categorical action spaces (e.g "left" or "right").

However, I am currently working with an action space that I discretized and the actions have an ordinal meaning (e.g. you can drive left or right in 5 degree increments). I assume that the action-value function has some monotonicity in the action component (think driving 45 degree to the left instead of 40 will have similar value). Am I losing information on the similarity of actions, if I use a network that has an output unit for each possible action? Are there implementations of the DQN available in which actions are used as network inputs?

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 will have three output units in your network). This makes a lot of sense from a computational standpoint and seems to work fine if you are dealing with categorical action spaces (e.g "left" or "right").

However, I am currently working with an action space that I discretized and the actions have an ordinal meaning (e.g. you can drive left or right in 5 degree increments). I assume that the action-value function has some monotonicity in the action component (think driving 45 degree to the left instead of 40 will have similar value). Am I losing information on the similarity of actions, if I use a network that has an output unit for each possible action? Are there implementations of the DQN available in which actions are used as network inputs?