A travel-cost value function defined via a proposed running cost is the unique bounded viscosity solution to a time-dependent HJB PDE whose negative sublevel set is the strict backward-reachable tube, and small-step RL value iteration converges to the forward discounted HJB solution.
Reachability-based safe learning with gaussian processes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unifying Hamilton-Jacobi Reachability and Reinforcement Learning
A travel-cost value function defined via a proposed running cost is the unique bounded viscosity solution to a time-dependent HJB PDE whose negative sublevel set is the strict backward-reachable tube, and small-step RL value iteration converges to the forward discounted HJB solution.