Keyphrases
- markov decision processes
- reinforcement learning
- factored mdps
- state space
- finite horizon
- travel time
- partially observable
- planning under uncertainty
- optimal policy
- decision theoretic planning
- markov decision problems
- markov decision process
- average cost
- policy iteration
- model based reinforcement learning
- finite state
- factored markov decision processes
- action sets
- decision processes
- dynamic programming
- semi markov decision processes
- probabilistic planning
- real time dynamic programming
- average reward
- action space
- decision diagrams
- dec pomdps
- machine learning
- initial state
- stochastic domains
- state and action spaces
- reinforcement learning algorithms
- reward function
- transition probabilities
- decision problems
- sufficient conditions