Reinforcement Learning via Recurrent Convolutional Neural Networks.
Tanmay ShankarSantosha K. DwivedyPrithwijit GuhaPublished in: CoRR (2017)
Keyphrases
- convolutional neural networks
- reinforcement learning
- convolutional network
- reinforcement learning algorithms
- learning algorithm
- model free
- function approximation
- recurrent neural networks
- markov decision processes
- feed forward
- multi agent
- temporal difference
- state space
- neural network
- machine learning
- database
- multi unit combinatorial auctions
- transfer learning
- optimal policy
- optimal control
- dynamic programming
- supervised learning
- action selection
- evolutionary algorithm