Selective experience replay in reinforcement learning for reidentification.
Ninad ThakoorBir BhanuPublished in: ICIP (2016)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- multi agent
- learning algorithm
- learning process
- multi agent reinforcement learning
- optimal policy
- markov decision processes
- optimal control
- model free
- personal experiences
- robotic control
- reinforcement learning methods
- partially observable
- database
- action selection
- user experience
- least squares
- dynamic programming
- image sequences
- data mining