Policy Invariance under Reward Transformations for General-Sum Stochastic Games.

Xiaosong Lu Howard M. Schwartz Sidney Nascimento Givigi

Published in: CoRR (2014)

Keyphrases

partially observable environments
reward function
image transformations
inverse reinforcement learning
reinforcement learning
average reward

policy gradient
expected reward
optimal policy
discounted reward
long run

control policy
agent receives
total reward
policy making
markov decision processes

bandit problems
data sets
partially observable
invariant features
multiscale