Extending symmetric variable-pair transitivities using state-space transformations.
Peter M. MaurerPublished in: ACM Great Lakes Symposium on VLSI (2012)
Keyphrases
- state space
- continuous time markov process
- optimal policy
- reinforcement learning
- state variables
- dynamical systems
- heuristic search
- dynamic programming
- markov decision processes
- pairwise
- particle filter
- orders of magnitude
- markov chain
- social networks
- search space
- reinforcement learning algorithms
- database
- state transition
- infinite horizon
- rendezvous search
- data sets