Monte Carlo Planning for Stochastic Control on Constrained Markov Decision Processes.
Larkin LiuShiqi LiuMatej JusupPublished in: CoRR (2024)
Keyphrases
- monte carlo
- markov decision processes
- partially observable
- state space
- markov chain
- finite state
- optimal policy
- policy evaluation
- reinforcement learning
- policy iteration
- dynamic programming
- planning problems
- infinite horizon
- particle filter
- partially observable markov decision processes
- reinforcement learning algorithms
- average cost
- markov decision process
- action space
- reward function
- optimal control
- markov decision problems
- control problems
- average reward
- transition probabilities
- stochastic games
- search space
- variance reduction
- brownian motion
- machine learning
- bayesian networks