Keyphrases
- reinforcement learning
- exploration exploitation tradeoff
- action selection
- active exploration
- learning process
- function approximation
- exploration strategy
- state space
- model based reinforcement learning
- objective function
- exploration exploitation
- information retrieval
- optimal policy
- database systems
- dynamic programming
- multi agent
- cost reduction
- storage cost
- expected cost
- active learning
- high cost
- minimum cost
- total cost
- optimal control
- markov decision processes
- least squares
- relevance feedback
- multi class