For SALE: State-Action Representation Learning for Deep Reinforcement Learning.
Scott FujimotoWei-Di ChangEdward J. SmithShixiang GuDoina PrecupDavid MegerPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- state action
- learning process
- learning algorithm
- state space
- optimal policy
- learning capabilities
- continuous state
- average reward
- learning agent
- evaluation function
- input output
- multi agent
- function approximation
- temporal difference
- partially observable
- action space
- supervised learning
- stochastic games
- active learning