Sketched Newton Value Iteration for Large-Scale Markov Decision Processes.
Jinsong LiuChenghan XieQi DengDongdong GeYinyu YePublished in: AAAI (2024)
Keyphrases
- markov decision processes
- state space
- reinforcement learning
- policy iteration
- optimal policy
- dynamic programming
- finite state
- transition matrices
- finite horizon
- model based reinforcement learning
- reachability analysis
- decision theoretic planning
- planning under uncertainty
- stochastic shortest path
- reinforcement learning algorithms
- average reward
- infinite horizon
- partially observable
- factored mdps
- risk sensitive
- decision processes
- average cost
- decision makers
- action space
- state and action spaces
- action sets
- learning algorithm
- markov decision process
- least squares