Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks.
Steven CarrNils JansenRalf WimmerAlexandru Constantin SerbanBernd BeckerUfuk TopcuPublished in: IJCAI (2019)
Keyphrases
- recurrent neural networks
- neural network
- recurrent networks
- feed forward
- reservoir computing
- echo state networks
- neural model
- feedforward neural networks
- artificial neural networks
- cascade correlation
- nonlinear dynamic systems
- state space
- model checking
- dynamic programming
- reinforcement learning
- complex valued
- markov decision processes
- significant improvement
- belief state
- genetic algorithm
- long short term memory
- biologically inspired
- distributed constraint optimization
- hebbian learning
- neural models
- probabilistic model
- machine learning