Preserving Stabilization while Practically Bounding State Space.
Vidhya Tekken ValapilSandeep S. KulkarniPublished in: CoRR (2017)
Keyphrases
- state space
- dynamic programming
- reinforcement learning
- heuristic search
- markov chain
- upper bound
- state variables
- orders of magnitude
- reinforcement learning algorithms
- dynamical systems
- search space
- markov decision processes
- continuous time markov process
- video stabilization
- planning problems
- optimal policy
- belief state
- particle filter
- initial state
- image details
- pattern databases
- goal state
- information retrieval
- real world