Discounted stochastic games for continuous-time jump processes with an uncountable state space.
Qingda WeiXian ChenPublished in: Math. Methods Oper. Res. (2022)
Keyphrases
- stochastic games
- state space
- markov decision processes
- markov chain
- average reward
- reinforcement learning algorithms
- optimal policy
- infinite horizon
- finite state
- reinforcement learning
- dynamic programming
- dynamical systems
- heuristic search
- policy iteration
- markov decision process
- repeated games
- state variables
- average cost
- finite horizon
- initial state
- partially observable
- action space
- search algorithm
- optimal control
- learning agent
- belief state
- search space
- transition probabilities
- long run
- stochastic processes
- cooperative
- multi agent
- nash equilibria
- learning algorithm
- planning problems
- probability distribution
- particle filter
- state transition
- decision problems
- machine learning
- function approximation