Feature Extraction for Decision-Theoretic Planning in Partially Observable Environments.
Hajime FujitaYutaka NakamuraShin IshiiPublished in: ICANN (1) (2006)
Keyphrases
- decision theoretic planning
- partially observable environments
- markov decision processes
- partially observable
- reinforcement learning algorithms
- markov decision problems
- reinforcement learning
- partially observable markov decision processes
- planning under uncertainty
- probabilistic planning
- inverse reinforcement learning
- state space
- decision problems
- finite state
- dynamic programming
- optimal policy
- learning algorithm
- infinite horizon
- policy iteration
- multi agent systems