Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding.
Alizée PaceHugo YècheBernhard SchölkopfGunnar RätschGuy TennenholtzPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- reinforcement learning algorithms
- markov decision processes
- direct policy search
- artificial intelligence
- learning algorithm
- robotic control
- state space
- real time
- machine learning
- case study
- reinforcement learning methods
- neural network
- action selection
- model free
- information retrieval
- multi agent
- learning problems
- partially observable
- control problems
- database