Keyphrases
- reinforcement learning
- multi agent
- function approximation
- belief networks
- cooperative
- state space
- markov random field
- learning algorithm
- model free
- action selection
- closed form
- multi agent reinforcement learning
- learning rate
- stochastic approximation
- statistical mechanics
- reinforcement learning algorithms
- em algorithm
- variational methods
- continuous time bayesian networks
- optimal policy
- bayesian inference
- reinforcement learning methods
- finite state
- fixed point
- free energy
- temporal difference learning
- belief propagation
- dynamic environments
- variational approximation
- markov chain