Does Zero-Shot Reinforcement Learning Exist?
Ahmed TouatiJérémy RapinYann OllivierPublished in: ICLR (2023)
Keyphrases
- reinforcement learning
- function approximation
- optimal control
- state space
- learning algorithm
- robotic control
- dynamic programming
- markov decision processes
- real world
- temporal difference
- reinforcement learning algorithms
- learning agents
- relational reinforcement learning
- machine learning
- supervised learning
- data mining
- partially observable
- function approximators
- temporal difference learning
- reinforcement learning methods
- policy search
- data sets