AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning.
Biwei HuangFan FengChaochao LuSara MagliacaneKun ZhangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- transfer learning
- knowledge transfer
- function approximation
- state space
- control problems
- adaptation process
- learning algorithm
- supervised learning
- markov decision processes
- model free
- cross domain
- optimal policy
- reinforcement learning algorithms
- multi agent
- genetic algorithm
- neural network
- real time
- temporal difference learning
- robot control
- robotic control
- multi agent reinforcement learning
- learning problems
- learning tasks
- knowledge sharing
- dynamic programming
- learning process
- social networks
- artificial intelligence
- data mining
- data sets