Temporal-difference learning for online reachability analysis.
Anayo K. AkametaluClaire J. TomlinPublished in: ECC (2015)
Keyphrases
- temporal difference learning
- reachability analysis
- markov decision processes
- function approximation
- fixed point
- model checking
- reinforcement learning
- policy iteration
- markov decision process
- game playing
- reinforcement learning algorithms
- evaluation function
- temporal difference
- timed automata
- state space
- incremental algorithms
- neural network