SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning.
Dohyeok LeeSeungyub HanTaehyun ChoJungwoo LeePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- computational model
- neural network
- dynamic programming
- classification models
- conceptual model
- experimental data
- mathematical model
- high level
- feature selection
- multi agent systems
- probability distribution
- state space
- bayesian networks
- theoretical framework
- statistical model
- learning algorithm
- formal model
- data sets