MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games.
Anran HuJunzi ZhangPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- learning agents
- online game
- video games
- matrix factorization
- closed form
- markov decision processes
- online learning
- action sets
- game playing
- educational games
- dynamic programming
- markov networks
- reinforcement learning agents
- statistical mechanics
- pairwise
- real time
- computer games
- state space
- collaborative filtering
- belief networks
- markov random field
- reinforcement learning algorithms
- variational methods
- learning process
- mobile robot
- role playing game
- continuous time bayesian networks