Iterative refinement of unknown MDP parameters allows repeated satisfaction of PAC conditions, yielding asymptotic optimality for reachability specifications in RL.
A pac learning algorithm for ltl and omega-regular objectives in mdps
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality
Iterative refinement of unknown MDP parameters allows repeated satisfaction of PAC conditions, yielding asymptotic optimality for reachability specifications in RL.