A Minimalist Approach to Offline Reinforcement Learning.
Scott FujimotoShixiang Shane GuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- real time
- reinforcement learning algorithms
- markov decision processes
- learning algorithm
- state space
- optimal policy
- model free
- machine learning
- robotic control
- multi agent
- perceptual aliasing
- optimal control
- multi agent reinforcement learning
- temporal difference
- reinforcement learning methods
- markov decision process
- learning classifier systems
- transition model
- function approximators
- database
- social networks
- databases
- learning process
- case study