Can Differentiable Decision Trees Learn Interpretable Reward Functions?

Akansha Kalra Daniel S. Brown

Published in: CoRR (2023)

Keyphrases

decision trees
reward function
classification rules
machine learning
hierarchical reinforcement learning
reinforcement learning
multiple agents
state space
optimal policy
objective function
transition probabilities
markov decision process
simple examples
prior knowledge
higher order
markov chain
data mining