A Policy Gradient Approach for Finite Horizon Constrained Markov Decision Processes.
Soumyajit GuinShalabh BhatnagarPublished in: CDC (2023)
Keyphrases
- markov decision processes
- finite horizon
- policy gradient
- reinforcement learning algorithms
- average reward
- reinforcement learning
- optimal policy
- actor critic
- partially observable markov decision processes
- finite state
- infinite horizon
- state space
- policy iteration
- average cost
- dynamic programming
- markov decision process
- function approximation
- optimal control
- reward function
- multistage
- state action
- gradient method
- action space
- control policies
- expected reward
- partially observable
- stochastic games
- machine learning
- function approximators
- variance reduction
- model free
- bayesian networks
- decision making