Regular Policies in Abstract Dynamic Programming.
Dimitri P. BertsekasPublished in: SIAM J. Optim. (2017)
Keyphrases
- dynamic programming
- optimal policy
- markov decision problems
- high level
- partially observable markov decision processes
- greedy algorithm
- state space
- linear programming
- higher level
- single machine
- multistage
- stereo matching
- lagrangian relaxation
- policy search
- control policies
- revenue management
- dynamic programming algorithms
- optimal control
- decision problems
- low level
- long run
- infinite horizon
- sequence alignment
- decision processes
- pairwise
- similarity measure
- e learning
- artificial intelligence