For SALE: State-Action Representation Learning for Deep Reinforcement Learning.
Scott FujimotoWei-Di ChangEdward J. SmithShixiang Shane GuDoina PrecupDavid MegerPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state action
- learning algorithm
- learning process
- stochastic games
- evaluation function
- active learning
- supervised learning
- state space
- function approximation
- learning capabilities
- multi agent
- policy gradient
- learning tasks
- neural network
- dynamic bayesian networks
- temporal difference
- action space
- function approximators
- multi agent systems
- continuous state