English

Formal Language Constraints for Markov Decision Processes

Machine Learning 2020-10-15 v3 Machine Learning

Abstract

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical situations. We study the benefits of giving structure to the constraints of a constrained Markov decision process by specifying them in formal languages as a step towards using safety methods from software engineering and controller synthesis. We instantiate these constraints as finite automata to efficiently recognise constraint violations. Constraint states are then used to augment the underlying MDP state and to learn a dense cost function, easing the problem of quickly learning joint MDP/constraint dynamics. We empirically evaluate the effect of these methods on training a variety of RL algorithms over several constraints specified in Safety Gym, MuJoCo, and Atari environments.

Keywords

Cite

@article{arxiv.1910.01074,
  title  = {Formal Language Constraints for Markov Decision Processes},
  author = {Eleanor Quint and Dong Xu and Samuel Flint and Stephen Scott and Matthew Dwyer},
  journal= {arXiv preprint arXiv:1910.01074},
  year   = {2020}
}

Comments

NeurIPS 2019 Workshop on Safety and Robustness in Decision Making

R2 v1 2026-06-23T11:32:58.324Z