MATLAB: Error on Specifying observation using rlFiniteSetSpec(Reinforcement Learning)

aidata scienceReinforcement Learning Toolboxsimulinkstatistics

When creating a simulink environment , for specify observation infomation of 2×1 double input(such as [5.0 ; 2.287]) , I used rlFiniteSetSpec([1 1]). And i got a error said "Invalid observation type or size". Any suggestions and help would be appreciated!

Best Answer

Hello,

The way you called rlFiniteSetSpec basically says that you have two observations and that they are both equal to 1. The values you are showing seem to be continuous though so I would recommend using rlNumericSpec instead.

Related Solutions

MATLAB: Implementation of Proximal Policy Optimisation

Hello,

It seems you want to use PPO with continuous action space. If that's the case, your actor network does not have the right architecture. With stochastic agents, the neural network should end with a path that outputs 'mean' value and another path that outputs 'variance'. In your case you seem to only have a single path. Please refer to this example here to get an idea on how to set up your actor network. Also make sure you are using 20a (PPO for continuous actions was not available in previous releases as far as I remember).

Hope that helps

MATLAB: Specifying Actions using rlFiniteSetSpec or rlNumericSpec (Reinforcement Learning)

Hi Huzaifah,

It is my understanding that have 4 actions (U, D, L, R) and want to specify them in your RL agent.

Generally, rlNumericSpec is used when you have a continuous action space and rlFiniteSetSpec is used when you have a discrete action space.

In your case, the action space is discrete. So, you should go with rlFiniteSetSpec.

As rlFiniteSetSpec takes only numeric input, you have to encode your actions to numbers. For example, (U,D,L,R) -> (1,2,3,4)

>> actInfo = rlFiniteSetSpec([1,2,3,4])  
actInfo = 
  rlFiniteSetSpec with properties:
       Elements: [4×1 double]
           Name: [0×0 string]
    Description: [0×0 string]
      Dimension: [1 1]
       DataType: "double"

For more information you can refer to : https://in.mathworks.com/help/reinforcement-learning/ref/rl.util.rlfinitesetspec.html

Best Answer

Related Solutions

MATLAB: Implementation of Proximal Policy Optimisation

MATLAB: Specifying Actions using rlFiniteSetSpec or rlNumericSpec (Reinforcement Learning)

Related Question