A Universal Empirical Dynamic Programming Algorithm for Continuous State MDPs.
William B. HaskellRahul JainHiteshi SharmaPengqian YuPublished in: IEEE Trans. Autom. Control. (2020)
Keyphrases
- continuous state
- reinforcement learning
- continuous state and action spaces
- policy search
- action space
- markov decision processes
- finite state
- continuous state spaces
- partially observable markov decision processes
- robot navigation
- state space
- planning problems
- control policies
- optimal policy
- function approximation
- machine learning
- state dependent
- markov chain
- reinforcement learning algorithms
- policy iteration
- dynamical systems
- average reward
- real valued
- control strategies
- markov decision problems
- control system
- decision problems
- multi agent
- learning algorithm