Proceedings of the 9th International Conference on Agents and Artificial Intelligence 2017
DOI: 10.5220/0006156001050117
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Markov Decision Processes. Abstract:We present a new reinforcement learning (RL) approach that enables an autonomous agent to solve decision making problems under constraints. Our assured reinforcement learning approach models the uncertain environment as a high-level, abstract Markov decision process (AMDP), and uses probabilistic model checking to establish AMDP policies that satisfy a set of constraints defined in probabilistic temporal logic. These formally verified abstract policies are then used to restr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
7
1
1

Relationship

1
8

Authors

Journals

citations
Cited by 27 publications
(13 citation statements)
references
References 24 publications
(39 reference statements)
0
13
0
Order By: Relevance
“…This area of future work was made possible by the recent adoption of our approach within several projects carried out by teams that include researchers and engineers not involved in the EvoChecker development. These projects have used or will use EvoChecker to devise safe reinforcement learning solutions (Mason et al 2017(Mason et al , 2018, to synthesise robust designs for software-based systems (Calinescu et al 2017b, c), and to suggest safe evacuation routes for communities affected by adverse events such as natural disasters. This will show how easy it is to define and validate EvoChecker models and requirements in real applications, allowing us to improve the usability of the approach.…”
Section: Discussionmentioning
confidence: 99%
“…This area of future work was made possible by the recent adoption of our approach within several projects carried out by teams that include researchers and engineers not involved in the EvoChecker development. These projects have used or will use EvoChecker to devise safe reinforcement learning solutions (Mason et al 2017(Mason et al , 2018, to synthesise robust designs for software-based systems (Calinescu et al 2017b, c), and to suggest safe evacuation routes for communities affected by adverse events such as natural disasters. This will show how easy it is to define and validate EvoChecker models and requirements in real applications, allowing us to improve the usability of the approach.…”
Section: Discussionmentioning
confidence: 99%
“…However, the calculation of inevitable collision states suffers from the curse of dimensionality. Another possibility is to apply logical reasoning, which uses deduction to prove correct behavior based on given rules [4], [5], [8]. However, logical reasoning is typically not appropriate for online verification, which is required in this work.…”
Section: B Safety Verification For Autonomous Vehiclesmentioning
confidence: 99%
“…Recently, formal approaches were proposed in order to restrict the exploration of the learning agent such that a set of logically constraints are always satisfied. This method can support other properties beyond safety, e.g., probabilistic computation tree logic (PCTL) [25,36], linear temporal logic (LTL) [1], or differential dynamic logic [17]. To the best of our knowledge, quantitative specifications have not yet been considered.…”
Section: Related Workmentioning
confidence: 99%