A Survey of Generalisation in Deep Reinforcement Learning.
Robert KirkAmy ZhangEdward GrefenstetteTim RocktäschelPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- temporal difference
- model free
- deep learning
- robotic control
- multi agent reinforcement learning
- learning process
- learning algorithm
- control problems
- neural network
- reinforcement learning algorithms
- supervised learning
- temporal difference learning
- machine learning
- robot control
- databases
- data sets
- autonomous learning
- reinforcement learning methods
- direct policy search
- action selection
- learning problems
- markov decision processes
- transfer learning
- optimal policy
- unsupervised learning
- dynamic programming
- search algorithm
- decision trees
- information systems