Getting children (and adults) to tidy up after themselves can be a challenge, but we face an even greater challenge trying to get our AI agents to do the same. Success depends on the mastery of several core visuo-motor skills: approaching an object, grasping and lifting it, opening a box and putting things inside of it. To make matters more complicated, these skills must be applied in the right sequence.
Control tasks, like tidying up a table or stacking objects, require an agent to determine how, when and where to coordinate the nine joints of its simulated arms and fingers to move correctly and achieve its objective. The sheer number of possible combinations of movements at any given time, along with the need to carry out a long sequence of correct actions constitute a serious exploration problem—making this a particularly interesting area for reinforcement learning research.
Techniques like reward shaping, apprenticeship learning or learning from demonstrations can help with the exploration problem. However, these methods rely on a considerable amount of knowledge about the task—the problem of learning complex control problems from scratch with minimal prior knowledge is still an open challenge.
Our new paper proposes a new learning paradigm called ‘Scheduled Auxiliary Control (SAC-X)’ which seeks to overcome this exploration issue. SAC-X is based on the idea that to learn complex tasks from scratch, an agent has to learn to explore and master a set of basic skills first. Just as a baby must develop coordination and balance before she crawls or walks—providing an agent with internal (auxiliary) goals corresponding to simple skills increases the chance it can understand and perform more complicated tasks.
