Login / Signup
Towards a more efficient computation of individual attribute and policy contribution for post-hoc explanation of cooperative multi-agent systems using Myerson values.
Giorgio Angelotti
Natalia Díaz Rodríguez
Published in:
CoRR (2022)
Keyphrases
</>
efficient computation
post hoc
attribute values
computational efficiency
cooperative multi agent systems
multi agent reinforcement learning
window search
optimal policy
machine learning
data sets
databases
data streams
dynamic programming
infinite horizon