Login / Signup
XAI and Strategy Extraction via Reward Redistribution.
Marius-Constantin Dinu
Markus Hofmarcher
Vihang P. Patil
Matthias Dorfer
Patrick M. Blies
Johannes Brandstetter
Jose A. Arjona-Medina
Sepp Hochreiter
Published in:
xxAI@ICML (2020)
Keyphrases
</>
optimal policy
markov decision processes
reinforcement learning
reward function
sufficient conditions
automatic extraction
information extraction
neural network
knowledge extraction
optimal strategy
databases
genetic algorithm
computer vision
three dimensional
special case
search strategy