Keyphrases
- reinforcement learning
- markov decision processes
- state space
- optimal policy
- function approximation
- dynamic programming
- model free
- partially observable
- finite state
- temporal difference
- continuous state and action spaces
- function approximators
- policy iteration
- markov decision process
- policy search
- machine learning
- state and action spaces
- constrained optimization
- constraint satisfaction
- dynamical systems
- action sets
- state abstraction
- reinforcement learning algorithms
- continuous state
- reinforcement learning methods
- average reward
- finite horizon
- optimal control
- learning algorithm
- continuous state spaces
- average cost
- reward function