Simulation Based Algorithms for Markov Decision Processes and Multi-Action Restless Bandits.
Rahul MeshramKesav KazaPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- policy iteration
- decision theoretic planning
- finite state
- reinforcement learning
- factored mdps
- state space
- reachability analysis
- dynamic programming
- optimal policy
- action space
- stochastic shortest path
- learning algorithm
- action sets
- continuous state spaces
- risk sensitive
- incremental algorithms
- discounted reward
- average reward
- transition matrices
- convergence rate