Continuous-action planning for discounted infinite-horizon nonlinear optimal control with Lipschitz values.
Lucian BusoniuElod PállRémi MunosPublished in: Autom. (2018)
Keyphrases
- infinite horizon
- optimal control
- partially observable markov decision processes
- production planning
- partially observable
- finite horizon
- dynamic programming
- single item
- continuous state
- control strategy
- reinforcement learning
- stochastic demand
- markov decision problems
- average cost
- markov decision process
- planning problems
- long run
- optimal policy
- policy iteration
- stochastic games
- machine learning
- markov decision processes
- state space