Approximate Value Iteration with Temporally Extended Actions.
Timothy A. MannShie MannorDoina PrecupPublished in: J. Artif. Intell. Res. (2015)
Keyphrases
- temporally extended
- approximate value iteration
- decision theoretic planning
- temporal logic
- qualitative simulation
- fixed point
- temporal difference learning
- temporal aspects
- classical planning
- markov decision processes
- markov decision problems
- qualitative reasoning
- markov chain
- model checking
- reinforcement learning algorithms
- function approximation
- evaluation function
- planning under uncertainty
- temporal information
- dynamical systems
- domain independent