Analytically Tractable Bayesian Deep Q-Learning.
Luong Ha NguyenJames-A. GouletPublished in: CoRR (2021)
Keyphrases
- belief nets
- multi agent
- reinforcement learning
- state space
- learning algorithm
- cooperative
- bayesian analysis
- function approximation
- bayesian networks
- bayesian estimation
- action selection
- posterior probability
- optimal policy
- np complete
- data driven
- data sets
- maximum likelihood
- bayesian inference
- temporal difference learning
- stochastic approximation
- dynamic programming
- reinforcement learning algorithms
- bayesian learning
- np hard
- potential field
- special case
- multi agent systems
- bayesian decision