IsoCost-Based Dynamic Programming for Solving Infinite Horizon Optimal Control Problems.
Saeed RahimiAmir Salimi LafmejaniAhmad KalhorPublished in: CoRR (2022)
Keyphrases
- infinite horizon
- optimal control
- optimal control problems
- dynamic programming
- production planning
- markov decision problems
- finite horizon
- stochastic demand
- partially observable
- optimal policy
- long run
- state space
- reinforcement learning
- knapsack problem
- markov decision processes
- average cost
- markov decision process
- dec pomdps
- control strategy
- machine learning
- policy iteration
- linear programming
- learning algorithm
- greedy algorithm
- combinatorial optimization
- partially observable markov decision processes