Fast Value Iteration for Goal-Directed Markov Decision Processes.
Nevin Lianwen ZhangWeihong ZhangPublished in: UAI (1997)
Keyphrases
- markov decision processes
- goal directed
- finite state
- policy iteration
- state space
- optimal policy
- dynamic programming
- transition matrices
- autonomous robots
- reachability analysis
- reinforcement learning
- finite horizon
- factored mdps
- action space
- average reward
- planning under uncertainty
- reinforcement learning algorithms
- markov decision process
- state and action spaces
- risk sensitive
- stochastic shortest path
- decision processes
- infinite horizon
- partially observable
- action sets
- total reward
- average cost