A Survey of Zero-shot Generalisation in Deep Reinforcement Learning.
Robert KirkAmy ZhangEdward GrefenstetteTim RocktäschelPublished in: J. Artif. Intell. Res. (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- learning algorithm
- temporal difference
- robot control
- stochastic approximation
- multi agent reinforcement learning
- multi agent
- decision making
- optimal control
- model free
- machine learning
- control problems
- robotic control
- reinforcement learning methods
- database
- learning agents
- optimal policy
- object recognition
- real time