Average cost optimal control under weak hypotheses: Relative value iterations.
Ari ArapostathisVivek S. BorkarPublished in: CoRR (2019)
Keyphrases
- optimal control
- average cost
- weak hypotheses
- infinite horizon
- risk sensitive
- dynamic programming
- finite horizon
- approximate dynamic programming
- markov decision chains
- control strategy
- weak learners
- optimal control problems
- reinforcement learning
- long run
- boosting algorithms
- markov decision processes
- markov decision process
- finite number
- real valued
- policy iteration
- state space
- probabilistic model
- pairwise
- optimal solution