Learning Neuro-Symbolic Skills for Bilevel Planning
This work addresses the problem of scalable and flexible decision-making for robotics, particularly in complex environments, though it builds incrementally on prior hierarchical planning approaches.
The paper tackles the challenge of decision-making in robotics with continuous states and actions by introducing a method to learn modular neuro-symbolic skills, including parameterized policies, operators, and samplers, which are sequenced using bilevel planning. In experiments across four robotics domains, it outperformed six baselines and ablations in solving diverse tasks.
Decision-making is challenging in robotics environments with continuous object-centric states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches, such as task and motion planning (TAMP), address these challenges by decomposing decision-making into two or more levels of abstraction. In a setting where demonstrations and symbolic predicates are given, prior work has shown how to learn symbolic operators and neural samplers for TAMP with manually designed parameterized policies. Our main contribution is a method for learning parameterized polices in combination with operators and samplers. These components are packaged into modular neuro-symbolic skills and sequenced together with search-then-sample TAMP to solve new tasks. In experiments in four robotics domains, we show that our approach -- bilevel planning with neuro-symbolic skills -- can solve a wide range of tasks with varying initial states, goals, and objects, outperforming six baselines and ablations. Video: https://youtu.be/PbFZP8rPuGg Code: https://tinyurl.com/skill-learning