Decision-Theoretic Planning with non-Markovian Rewards
Charles GrettonFroduald KabanzaDavid PriceJohn K. SlaneySylvie ThiébauxPublished in: CoRR (2011)
Keyphrases
- decision theoretic planning
- markov decision processes
- temporally extended
- decision processes
- reinforcement learning
- reward function
- state space
- finite state
- markov decision process
- reinforcement learning algorithms
- markov decision problems
- optimal policy
- policy iteration
- dynamic programming
- planning under uncertainty
- partially observable
- action space
- average cost
- function approximation
- probabilistic planning
- multi agent
- model free
- decision problems
- average reward
- machine learning