# Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation

arXiv: https://arxiv.org/abs/1912.01649 · HTML: https://mlsanity.com/paper/1912.01649/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 4 of 4)

- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [RLIF: Interactive Imitation Learning as Reinforcement Learning](https://mlsanity.com/paper/2311.12996/) (2023)
- [Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback](https://mlsanity.com/paper/2310.20608/) (2023)
- [The Geometry of Learning to Avoid Interventions](https://mlsanity.com/paper/2602.03825/) (2026)

## Abstract (arXiv)

In many environments, only a relatively small subset of the complete state space is necessary in order to accomplish a given task. We develop a simple technique using emergency stops (e-stops) to exploit this phenomenon. Using e-stops significantly improves sample complexity by reducing the amount of required exploration, while retaining a performance bound that efficiently trades off the rate of convergence with a small asymptotic sub-optimality gap. We analyze the regret behavior of e-stops and present empirical results in discrete and continuous settings demonstrating that our reset mechanism can provide order-of-magnitude speedups on top of existing reinforcement learning methods.