Tight Continuous-Time Reachtubes for Lagrangian Reachability.
Jacek CyrankaMd. Ariful IslamScott A. SmolkaSicun GaoRadu GrosuPublished in: CoRR (2018)
Keyphrases
- state space
- lower bound
- markov chain
- upper bound
- worst case
- optimal control
- iterative learning control
- reinforcement learning
- optimal solution
- transitive closure
- lagrangian relaxation
- markov processes
- dynamical systems
- artificial intelligence
- prize collecting
- stochastic processes
- non stationary
- generalization error bounds
- database