Transfer Reinforcement Learning with Shared Dynamics.
Romain LarocheMerwan BarlierPublished in: AAAI (2017)
Keyphrases
- reinforcement learning
- transfer learning
- state space
- function approximation
- knowledge transfer
- dynamic model
- learning algorithm
- temporal evolution
- markov decision processes
- control problems
- multi agent
- action selection
- learning tasks
- robot control
- collective behavior
- stochastic approximation
- highly nonlinear
- model free
- neural network
- sufficient conditions
- dynamic programming
- decision trees
- information systems
- machine learning