Scientific Discovery and the Cost of Measurement - Balancing Information and Cost in Reinforcement Learning.
Colin BellingerAndriy DrozdyukMark CrowleyIsaac TamblynPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- scientific discovery
- end users
- information acquisition
- information processing
- learning algorithm
- high cost
- total cost
- structural information
- contextual information
- higher level
- information overload
- cost sensitive
- information sources
- database
- dynamic programming
- wireless sensor networks
- domain knowledge
- prior knowledge
- genetic algorithm
- real world