Bayesian Q-learning With Imperfect Expert Demonstrations.
Fengdi CheXiru ZhuDoina PrecupDavid MegerGregory DudekPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning algorithm
- multi agent
- cooperative
- function approximation
- state space
- maximum likelihood
- bayesian networks
- reinforcement learning algorithms
- gaussian processes
- domain experts
- bayesian inference
- learning rate
- expert advice
- human experts
- bayesian decision
- posterior probability
- expert knowledge
- model free
- action selection
- stochastic approximation
- path planning
- bayesian learning
- bayesian estimation
- multi agent reinforcement learning