Reinforcement Learning Neural Turing Machines.
Wojciech ZarembaIlya SutskeverPublished in: CoRR (2015)
Keyphrases
- turing machine
- reinforcement learning
- fitted q iteration
- network architecture
- function approximation
- neural network
- multi agent
- temporal difference
- state space
- artificial neural
- neural model
- temporal difference learning
- model free
- associative memory
- optimal policy
- learning agents
- data sets
- neural computation
- learning algorithm
- function approximators
- markov decision process
- learning problems
- action selection
- learning rules
- dynamic programming
- partially observable
- biologically inspired
- markov decision processes
- sensory inputs
- multi agent reinforcement learning
- hebbian learning
- robotic control
- neural information processing
- artificial neural networks