Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch.

Michael Wan Tanmay Gangwani Jian Peng

Published in: UAI (2020)

Keyphrases

knowledge transfer
state action
reinforcement learning
evaluation function
transfer learning
knowledge sharing
action space
average reward
stochastic games
learning tasks
state transitions
markov decision process
belief state
reward function
state space
markov decision processes
decision trees
data mining