Planning Problem for Continuous-Time Finite State Mean Field Game with Compact Action Space.
Yurii V. AverboukhAleksei VolkovPublished in: Dyn. Games Appl. (2024)
Keyphrases
- finite state
- continuous time bayesian networks
- action space
- markov decision processes
- state space
- markov chain
- continuous state
- partially observable markov decision processes
- stochastic processes
- planning problems
- stochastic games
- partially observable
- heuristic search
- optimal policy
- reinforcement learning
- action selection
- markov processes
- markov decision problems
- dynamic programming
- markov decision process
- markov random field
- average cost
- real valued
- policy iteration
- stationary policies
- reinforcement learning algorithms
- initial state
- domain independent
- average reward
- belief state
- state action
- dynamical systems
- belief networks
- infinite horizon
- decision problems
- model checking
- reward function
- probability distribution