64 lines
2.3 KiB
Markdown
64 lines
2.3 KiB
Markdown
---
|
||
authors:
|
||
|
||
- "Alshiekh, Mohammed"
|
||
|
||
- "Bloem, Roderick"
|
||
|
||
- "Ehlers, Rüdiger"
|
||
|
||
- "Könighofer, Bettina"
|
||
|
||
- "Niekum, Scott"
|
||
|
||
- "Topcu, Ufuk"
|
||
|
||
citekey: "alshiekhSafeReinforcementLearning2018"
|
||
publish_date: 2018-04-29
|
||
journal: "Proceedings of the AAAI Conference on Artificial Intelligence"
|
||
volume: 32
|
||
issue: 1
|
||
last_import: 2025-05-15
|
||
---
|
||
|
||
# Indexing Information
|
||
Published: 2018-04
|
||
|
||
**DOI**
|
||
[10.1609/aaai.v32i1.11797](https://doi.org/10.1609/aaai.v32i1.11797)
|
||
#Formal-Methods
|
||
|
||
|
||
#InFirstPass
|
||
|
||
|
||
|
||
>[!Abstract]
|
||
>Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties expressed in temporal logic. To this end, given the temporal logic specification that is to be obeyed by the learning system, we propose to synthesize a reactive system called a shield. The shield monitors the actions from the learner and corrects them only if the chosen action causes a violation of the specification. We discuss which requirements a shield must meet to preserve the convergence guarantees of the learner. Finally, we demonstrate the versatility of our approach on several challenging reinforcement learning scenarios.>[!seealso] Related Papers
|
||
>
|
||
|
||
# Annotations
|
||
## Notes
|
||
![[Safe Reinforcement Learning via Shielding-Note]]
|
||
|
||
## Highlights From Zotero
|
||
|
||
|
||
|
||
|
||
>[!highlight] Highlight
|
||
> . Increasing use of learning-based controllers inphysical systems in the proximity of humans strengthens theconcern of whether these systems will operate safely.
|
||
> 2025-05-13 4:28 pm
|
||
|
||
>[!tip] Brilliant
|
||
> In this paper, we introduce shielded learning, a frame-work that allows applying machine learning to control sys-tems in a way that the correctness of the system’s executionagainst a given specification is assured during the learningand controller execution phases, regardless of how fast the learning process converges. The shield monitors the actionsselected by the learning agent and corrects them if and onlyif the chosen action is unsafe.
|
||
> 2025-05-13 4:29 pm
|
||
|
||
>[!done] Important
|
||
> Last but not least, the shieldingframework is compatible with mechanisms such as functionapproximation, employed by learning algorithms in order to improve their scalability.
|
||
> 2025-05-13 4:31 pm
|
||
|
||
|
||
## Follow-Ups
|
||
|