Where To Start? Transferring Simple Skills to Complex Environments

Such skills can be learnt through methods such as imitation learning [1] or reinforce ment learning [2]. However, since these methods are data-driven, they would require training across a huge range of environments if the task is to execute the skills whilst avoiding collisions with the environment. And since this is typically impractical, these skills are typically trained in open, unconstrained environments, without enabling transfer of the skill to more complex, cluttered environments. This then raises the following question: how do we maintain the high performance of a skill that was trained in obstacle-free environments, whilst ensuring that it does not collide with obstacles in new cluttered environments? In complex environments, reactively avoiding obstacles by adding small control adjustments to a learned skill might not be enough, resulting in a need to completely alter the skill and re-learn how to complete the task in the new environment.