Decision-Theoretic Planning with non-Markovian Rewards.
Sylvie ThiébauxCharles GrettonJohn K. SlaneyDavid PriceFroduald KabanzaPublished in: J. Artif. Intell. Res. (2006)
Keyphrases
- decision theoretic planning
- markov decision processes
- temporally extended
- reinforcement learning
- decision processes
- reward function
- state space
- finite state
- optimal policy
- markov decision problems
- markov decision process
- dynamic programming
- reinforcement learning algorithms
- planning under uncertainty
- partially observable
- policy iteration
- function approximation
- average cost
- average reward
- action space
- infinite horizon
- situation calculus
- machine learning