source/MXNetEnv/training/training_src/networks/utils.py [29:43]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        output_states = np.zeros(shape=(state.shape[0],
                                        state.shape[1],
                                        3))
        output_states[:, :, 0] = food_state
        output_states[:, :, 1] = self_state
        if other_states[0, 0, 0] == -1: # if states are bordered
            output_states[:, :, 2] = -1

            # Find all values excluding the border, assuming borders are -1
            other_states = np.sum(other_states, axis=2)
            other_states[other_states<0] = -1

            output_states[:, :, 2] = other_states
        else:
            output_states[:, :, 2] = np.sum(other_states, axis=2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



source/RLlibEnv/training/training_src/utils.py [26:41]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    output_states = np.zeros(shape=(state.shape[0],
                                    state.shape[1],
                                    3))
    output_states[:, :, 0] = food_state
    output_states[:, :, 1] = self_state
        
    if other_states[0, 0, 0] == -1: # if states are bordered
        output_states[:, :, 2] = -1

        # Find all values excluding the border, assuming borders are -1
        other_states = np.sum(other_states, axis=2)
        other_states[other_states<0] = -1
        
        output_states[:, :, 2] = other_states
    else:
        output_states[:, :, 2] = np.sum(other_states, axis=2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -