Fast Value Iteration for Goal-Directed Markov Decision Processes
Nevin Lianwen ZhangWeihong ZhangPublished in: CoRR (2013)
Keyphrases
- goal directed
- markov decision processes
- policy iteration
- state space
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- transition matrices
- reachability analysis
- decision theoretic planning
- autonomous robots
- planning under uncertainty
- average reward
- finite horizon
- decision processes
- state and action spaces
- risk sensitive
- action space
- markov decision process
- reinforcement learning algorithms
- factored mdps
- infinite horizon
- action sets
- average cost
- partially observable
- probabilistic planning
- reward function
- markov chain
- discount factor
- model based reinforcement learning
- evaluation function