Symbolic State Partitioning for Reinforcement Learning
This work addresses a domain-specific challenge in reinforcement learning for continuous environments, offering an incremental improvement over existing partitioning methods.
The paper tackles the problem of tabular reinforcement learning on continuous state spaces by partitioning the state space using symbolic execution, which improves state space coverage and enhances learning performance for sparse rewards.
Tabular reinforcement learning methods cannot operate directly on continuous state spaces. One solution for this problem is to partition the state space. A good partitioning enables generalization during learning and more efficient exploitation of prior experiences. Consequently, the learning process becomes faster and produces more reliable policies. However, partitioning introduces approximation, which is particularly harmful in the presence of nonlinear relations between state components. An ideal partition should be as coarse as possible, while capturing the key structure of the state space for the given problem. This work extracts partitions from the environment dynamics by symbolic execution. We show that symbolic partitioning improves state space coverage with respect to environmental behavior and allows reinforcement learning to perform better for sparse rewards. We evaluate symbolic state space partitioning with respect to precision, scalability, learning agent performance and state space coverage for the learnt policies.