Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning
This addresses a key bottleneck for reinforcement learning agents in domains requiring both planning and control, such as robotics, though it builds incrementally on hierarchical methods.
The paper tackles the challenge of combining long-horizon planning with continuous control in reinforcement learning by introducing SEADS, a hierarchical agent that learns temporally extended skills and a symbolic forward model, achieving high success rates in complex tasks and outperforming baseline agents.
Problems which require both long-horizon planning and continuous control capabilities pose significant challenges to existing reinforcement learning agents. In this paper we introduce a novel hierarchical reinforcement learning agent which links temporally extended skills for continuous control with a forward model in a symbolic discrete abstraction of the environment's state for planning. We term our agent SEADS for Symbolic Effect-Aware Diverse Skills. We formulate an objective and corresponding algorithm which leads to unsupervised learning of a diverse set of skills through intrinsic motivation given a known state abstraction. The skills are jointly learned with the symbolic forward model which captures the effect of skill execution in the state abstraction. After training, we can leverage the skills as symbolic actions using the forward model for long-horizon planning and subsequently execute the plan using the learned continuous-action control skills. The proposed algorithm learns skills and forward models that can be used to solve complex tasks which require both continuous control and long-horizon planning capabilities with high success rate. It compares favorably with other flat and hierarchical reinforcement learning baseline agents and is successfully demonstrated with a real robot.