Deep Reinforcement Learning with Averaged Target DQN.
Oron AnschelNir BaramNahum ShimkinPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- learning algorithm
- function approximation
- learning process
- reinforcement learning algorithms
- genetic algorithm
- optimal control
- previously learned
- machine learning
- model free
- state space
- robotic control
- real time
- temporal difference
- markov decision processes
- multi agent
- computer vision
- information retrieval
- neural network
- data sets