It has been shown that deep approaches to learning, intrinsic motivation, and self-regulated learning have strong positive effects on learning. How those pedagogical theories can be integrated in computing curricula is, however, still lacking empirically grounded analyses. This study integrated, in a robotics-based programming class, a method of learning-by-inventing, and studied its qualitative effects on students’ learning through 144 interviews. Five findings were related with learning theories: changes in students’ problem management cycle, problem-rich learning environment, conceptions of the nature of computing, extension of deep and surface approaches to problem solving and management, and the use of robotics to facilitate deep learning strategies. Our analysis suggests that a combination of an open learning environment, robotics as the learning tool, and learning-by-inventing provides a conducive environment for deep learning strategies, intrinsic motivation, and self-regulated learning, which are prerequisite conditions for creativity and inventing.