I'm a beginner for gym RL framework and currently setting up a reinforcement learning environment using the gym. I'm totally confused about how I need to set my observation space. Since my problem is a binary classification problem, I'm don't have any issue with action space. It's DISCRETE(2).
For observations, agents getting 4 inputs from the environment and all four are arrays, and following are the shapes of those arrays.
Observation 1: (150,) --> i.e. array([ 0, 0, 0, 0,..., 2, 1, 21],dtype=int32)
Observation 2: (614, 2) --> i.e. array([[ 0.10108147, 0.27550402],[-0.26806018, -0.42727235],...,[-0.24262361, 0.04642992]])
Observation 3: TensorShape([614, 614]) --> i.e. <tensorflow.python.framework.sparse_tensor.SparseTensor at 0x7f2d2b7bc190>
Observation 4: (614,) --> i.e. array([0, 0, 0, 0, 0,...,0, 0])
Can anyone help me to define the observation_space for the above 4 observations?
