Keyphrases
- markov decision processes
- reinforcement learning
- state space
- factored mdps
- fully observable
- markov decision problems
- finite horizon
- stochastic domains
- dynamic programming
- optimal policy
- data sets
- black box
- decision theoretic planning
- model based reinforcement learning
- randomized algorithms
- probabilistic planning
- planning under uncertainty
- average reward
- infinite horizon
- search space
- machine learning