AMLAS-RL defines six stages for generating RL safety assurance arguments, demonstrated on a wheeled vehicle where verification ultimately showed the need to revisit earlier stages.
Deep reinforcement learning: An overview,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Assuring the Safety of Reinforcement Learning Components: AMLAS-RL
AMLAS-RL defines six stages for generating RL safety assurance arguments, demonstrated on a wheeled vehicle where verification ultimately showed the need to revisit earlier stages.