CHIME: An Adaptive Hierarchical Representation for Continuous Intrinsically Motivated Exploration

For a life-long learning, robots need to learn and adapt to the environment to complete multiple tasks ranging from low-level to high-level tasks, using simple actions or complex ones. Current intrinsically motivated solutions often rely on fixed representations of this environment to define possible tasks, limiting the possibility to adapt to new or changing ones. We propose an algorithm that is able to autonomously 1) self-discover tasks to learn in its environment 2) discover the relationship between tasks to leverage its acquired knowledge on low-level tasks to solve high-level tasks 3) devise a sequence of policies of unbounded length to complete the tasks. Our algorithm, named Continual Hierarchical Intrinsically Motivated Exploration (CHIME), uses planning to build chains of actions, the learning of a hierarchical representation of tasks to reuse low-level skills for high-level tasks and intrinsically-motivatd goal babbling to discover new subtasks and orient its learning in its high-dimensional continuous environment. To highlight the features of CHIME, we implement it in a simulated mobile robot where it can move and place objects.