AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning.
Biwei HuangFan FengChaochao LuSara MagliacaneKun ZhangPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- transfer learning
- adaptation process
- model free
- function approximation
- knowledge transfer
- reinforcement learning algorithms
- changing environment
- optimal control
- temporal difference learning
- multi agent
- state space
- temporal difference
- markov decision processes
- previously learned
- transferring knowledge
- direct policy search
- control problems
- learning algorithm
- genetic algorithm
- real time
- learning tasks
- collaborative filtering
- dynamic programming
- evolutionary algorithm
- artificial neural networks
- search algorithm
- learning environment
- objective function
- robotic control
- database