A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints.

Krishna Chaitanya Kalagarla Rahul Jain Pierluigi Nuzzo

Published in: AAAI (2021)

Keyphrases

finite horizon
learning algorithm
dynamic programming
objective function
computational complexity
multistage
markov decision processes
optimal solution
np hard
expectation maximization
optimal policy
mathematical model
hidden markov models
probabilistic model
knapsack problem