Keyphrases
- average reward
- markov decision processes
- discounted reward
- reinforcement learning
- total reward
- optimal policy
- reward function
- stochastic games
- policy iteration
- semi markov decision processes
- long run
- optimality criterion
- state space
- finite state
- model free
- state and action spaces
- average cost
- dynamic programming
- reinforcement learning algorithms
- decision makers
- hierarchical reinforcement learning
- machine learning
- partially observable
- multi agent
- dynamical systems