Login / Signup
Handling different level of unstable reward environment through an estimation of reward distribution in XCS.
Takato Tatsumi
Takahiro Komine
Hiroyuki Sato
Keiki Takadama
Published in:
CEC (2015)
Keyphrases
</>
reinforcement learning
long run
initially unknown
parameter estimation
reward function
partial knowledge
agent receives
levels of abstraction
uniformly distributed
classifier systems
mobile robot
probability distribution
virtual world
random variables
inverse reinforcement learning