Balancing exploration and exploitation ratio in reinforcement learning.
Ozkan OzcanClaudio Coreixas de MoraesJonathan K. AltPublished in: SpringSim (MMS) (2011)
Keyphrases
- balancing exploration and exploitation
- reinforcement learning
- learning to rank
- function approximation
- state space
- model free
- reinforcement learning algorithms
- machine learning
- transfer learning
- reinforcement learning methods
- optimal policy
- learning algorithm
- data sets
- markov decision processes
- supervised learning
- standard deviation
- temporal difference
- robotic control
- neural network
- loss function
- learning problems
- classification accuracy
- multi agent
- information retrieval
- policy search