Shallow Updates for Deep Reinforcement Learning.
Nir LevineTom ZahavyDaniel J. MankowitzAviv TamarShie MannorPublished in: NIPS (2017)
Keyphrases
- reinforcement learning
- function approximation
- state space
- natural language processing
- robotic control
- question answering
- model free
- temporal difference
- multi agent reinforcement learning
- deep learning
- reinforcement learning methods
- information extraction
- temporal difference learning
- multi agent
- learning algorithm
- machine learning
- optimal control
- markov decision processes
- supervised learning
- information retrieval
- neural network
- reinforcement learning algorithms
- partially observable
- optimal policy
- hand crafted
- stochastic approximation
- autonomous learning
- multi agent systems
- direct policy search
- wall street journal