Changing Model Behavior at Test-time Using Reinforcement Learning.
Augustus OdenaDieterich LawsonChristopher OlahPublished in: ICLR (Workshop) (2017)
Keyphrases
- high level
- computational model
- reinforcement learning
- probabilistic model
- simulation model
- management system
- parameter estimation
- case study
- mathematical model
- statistical model
- experimental data
- structural equation modeling
- physical systems
- dynamic behavior
- prediction model
- test data
- probability distribution
- control system
- multi agent