Incremental plan aggregation for generating policies in MDPs.
Florent Teichteil-KönigsbuchUgur KuterGuillaume InfantesPublished in: AAMAS (2010)
Keyphrases
- optimal policy
- markov decision processes
- markov decision process
- markov decision problems
- reward function
- reinforcement learning
- initial state
- incremental learning
- policy search
- state space
- average cost
- finite horizon
- decision theoretic
- decision processes
- factored mdps
- plan execution
- dynamic programming
- infinite horizon
- plan recognition
- decision problems
- policy iteration
- long run
- partially observable
- ai planning
- planning process
- plan generation
- control policies
- total cost
- continuous state
- utility function