# Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning

arXiv: https://arxiv.org/abs/2306.17033 · HTML: https://mlsanity.com/paper/2306.17033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 12 of 12)

- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods](https://mlsanity.com/paper/2202.11762/) (2022)
- [A Composable Specification Language for Reinforcement Learning Tasks](https://mlsanity.com/paper/2008.09293/) (2020)
- [Compositional Reinforcement Learning from Logical Specifications](https://mlsanity.com/paper/2106.13906/) (2021)
- [A Boolean Task Algebra for Reinforcement Learning](https://mlsanity.com/paper/2001.01394/) (2020)
- [Hierarchical Potential-based Reward Shaping from Task Specifications](https://mlsanity.com/paper/2110.02792/) (2021)
- [Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives](https://mlsanity.com/paper/2202.02404/) (2022)

## Abstract (arXiv)

Compositionality is a critical aspect of scalable system design. Reinforcement learning (RL) has recently shown substantial success in task learning, but has only recently begun to truly leverage composition. In this paper, we focus on Boolean composition of learned tasks as opposed to functional or sequential composition. Existing Boolean composition for RL focuses on reaching a satisfying absorbing state in environments with discrete action spaces, but does not support composable safety (i.e., avoidance) constraints. We advance the state of the art in Boolean composition of learned tasks with three contributions: i) introduce two distinct notions of safety in this framework; ii) show how to enforce either safety semantics, prove correctness (under some assumptions), and analyze the trade-offs between the two safety notions; and iii) extend Boolean composition from discrete action spaces to continuous action spaces. We demonstrate these techniques using modified versions of value iteration in a grid world, Deep Q-Network (DQN) in a grid world with image observations, and Twin Delayed DDPG (TD3) in a continuous-observation and continuous-action Bullet physics environment. We believe that these contributions advance the theory of safe reinforcement learning by allowing zero-shot composition of policies satisfying safety properties.