Continuous-Time q-learning for McKean-Vlasov Control Problems.
Xiaoli WeiXiang YuPublished in: CoRR (2023)
Keyphrases
- control problems
- reinforcement learning
- optimal control
- state space
- continuous state spaces
- reinforcement learning methods
- dynamic programming
- function approximation
- policy iteration
- markov chain
- rl algorithms
- optimal policy
- model free
- queueing systems
- reinforcement learning algorithms
- stochastic control
- cooperative
- action selection
- learning algorithm
- control strategy
- markov decision processes
- continuous state
- multi agent
- temporal difference
- machine learning
- temporal difference learning
- infinite horizon
- real time
- markov processes
- dynamical systems
- state action
- learning agent
- brownian motion
- approximate dynamic programming
- data mining
- control method