Lipschitz Continuity in Model-based Reinforcement Learning.
Kavosh AsadiDipendra MisraMichael L. LittmanPublished in: CoRR (2018)
Keyphrases
- model based reinforcement learning
- lipschitz continuity
- set valued
- markov decision processes
- variational inequalities
- semidefinite
- reinforcement learning
- dominance relation
- state space
- sufficient conditions
- rough sets
- belief functions
- convex relaxation
- linear complementarity problem
- markov decision problems
- dynamic programming
- special case