The following pages link to (Q5089265):
Displaying 10 items.
- Runtime monitors for Markov decision processes (Q832291) (← links)
- Enforcing almost-sure reachability in POMDPs (Q832296) (← links)
- Lifted model checking for relational MDPs (Q2102421) (← links)
- Safe Exploration of State and Action Spaces in Reinforcement Learning (Q4899127) (← links)
- Risk-aware shielding of partially observable Monte Carlo planning policies (Q6088298) (← links)
- Dynamic shielding for reinforcement learning in black-box environments (Q6103158) (← links)
- Safety-constrained reinforcement learning with a distributional safety critic (Q6106435) (← links)
- A learner-verifier framework for neural network controllers and certificates of stochastic systems (Q6535337) (← links)
- Deductive controller synthesis for probabilistic hyperproperties (Q6546464) (← links)
- DSMC evaluation stages: fostering robust and safe behavior in deep reinforcement learning -- extended version (Q6599368) (← links)
