Learning by Cheating : An End-to-End Zero Shot Framework for Autonomous Drone Navigation
This provides a method for reusing simple policies in complex tasks, potentially benefiting robotics and reinforcement learning applications, though it appears incremental in approach.
The paper tackles autonomous drone navigation in cluttered environments by learning control policies in a low-level training environment and applying them to more complex settings during inference, tricking the controller into believing it is still in the simpler environment.
This paper proposes a novel framework for autonomous drone navigation through a cluttered environment. Control policies are learnt in a low-level environment during training and are applied to a complex environment during inference. The controller learnt in the training environment is tricked into believing that the robot is still in the training environment when it is actually navigating in a more complex environment. The framework presented in this paper can be adapted to reuse simple policies in more complex tasks. We also show that the framework can be used as an interpretation tool for reinforcement learning algorithms.