Disentangling Transfer in Continual Reinforcement Learning.
Maciej WolczykMichal ZajacRazvan PascanuLukasz KucinskiPiotr MilosPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- transfer learning
- knowledge transfer
- function approximation
- machine learning
- markov decision processes
- multi agent
- model free
- state space
- artificial intelligence
- information retrieval
- direct policy search
- temporal difference
- learning classifier systems
- cross domain
- learning algorithm
- active learning
- learning process
- learning problems
- learning tasks
- real time
- optimal policy
- control problems
- learning agents
- temporal difference learning
- e learning