Reinforcement Learning via Recurrent Convolutional Neural Networks.
Tanmay ShankarSantosha K. DwivedyPrithwijit GuhaPublished in: ICPR (2016)
Keyphrases
- convolutional neural networks
- reinforcement learning
- convolutional network
- function approximation
- learning algorithm
- reinforcement learning algorithms
- state space
- model free
- optimal policy
- temporal difference learning
- recurrent neural networks
- dynamic programming
- multi agent
- markov decision processes
- supervised learning
- multi agent reinforcement learning
- data sets
- temporal difference
- multi unit combinatorial auctions
- learning capabilities
- feed forward
- transfer learning
- image database
- case study
- genetic algorithm