Finite State Transducers for Policy Evaluation and Conflict Resolution.
Javier BaliosianJoan SerratPublished in: POLICY (2004)
Keyphrases
- conflict resolution
- policy evaluation
- finite state transducers
- finite state
- markov decision processes
- policy iteration
- partially observable markov decision processes
- least squares
- monte carlo
- temporal difference
- reinforcement learning
- optimal policy
- language modeling
- n gram
- machine translation
- model free
- resolve conflicts
- variance reduction
- resolving conflicts
- markov chain
- function approximation
- language model
- hidden markov models
- semi parametric
- grammatical inference
- dynamic programming
- model checking
- state space
- neural network
- query expansion
- edit distance
- statistical inference
- probabilistic model
- text mining
- evaluation function
- multi agent systems
- pattern recognition
- data mining
- dynamical systems