Optimal exploration strategies for finite horizon regret minimization in some adaptive control problems.
Kévin ColinHåkan HjalmarssonXavier BomboisPublished in: CoRR (2022)
Keyphrases
- finite horizon
- control problems
- optimal control
- infinite horizon
- optimal stopping
- regret minimization
- average cost
- reinforcement learning
- optimal policy
- adaptive control
- single product
- dynamic programming
- brownian motion
- markov decision processes
- control policies
- multistage
- stochastic control
- markov decision process
- non stationary
- optimal strategy
- inventory policy
- nash equilibrium
- control strategy
- state space
- optimal solution
- real time