Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics
This work addresses data efficiency in robotics for researchers and practitioners, presenting an incremental improvement by combining existing approaches.
The paper tackles the problem of high data demand in robotics reinforcement learning by integrating RL with model-based planning to create universal plan-conditioned policies, resulting in increased performance in robotic manipulation experiments compared to pure RL, pure planning, or baseline methods.
Applications of Reinforcement Learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenarios, making model-based approaches like planning a data-efficient alternative. Still, the performance of these methods suffers if the model is imprecise or wrong. In this sense, the respective strengths and weaknesses of RL and model-based planners are. In the present work, we investigate how both approaches can be integrated into one framework that combines their strengths. We introduce Learning to Execute (L2E), which leverages information contained in approximate plans to learn universal policies that are conditioned on plans. In our robotic manipulation experiments, L2E exhibits increased performance when compared to pure RL, pure planning, or baseline methods combining learning and planning.