Preserving stabilization while practically bounding state space using incorruptible partially synchronized clocks.
Vidhya Tekken ValapilSandeep S. KulkarniPublished in: Distributed Comput. (2020)
Keyphrases
- state space
- heuristic search
- reinforcement learning
- markov chain
- markov decision processes
- reinforcement learning algorithms
- upper bound
- dynamic programming
- particle filter
- optimal policy
- dynamical systems
- continuous state spaces
- real time
- belief state
- goal state
- orders of magnitude
- markov decision process
- action space
- image details
- video stabilization
- markov decision problems
- reward function
- planning problems
- multiscale