Change memory size definition in docs

docs/Training-PPO.md

 ### Memory Size
 
 `memory_size` corresponds to the size of the array of floating point numbers
-used to store the hidden state of the recurrent neural network. This value must
+used to store the hidden state of the recurrent neural network of the policy. This value must
-Typical Range: `64` - `512`
+Typical Range: `32` - `256`
 
 ## (Optional) Behavioral Cloning Using Demonstrations
 

docs/Training-SAC.md

 ### Memory Size
 
 `memory_size` corresponds to the size of the array of floating point numbers
-used to store the hidden state of the recurrent neural network. This value must
-be a multiple of 4, and should scale with the amount of information you expect
+used to store the hidden state of the recurrent neural network in the policy.
+This value should scale with the amount of information you expect
-Typical Range: `64` - `512`
+Typical Range: `32` - `256`
 
 ### (Optional) Save Replay Buffer