Learning in Observable POMDPs, without Computationally Intractable Oracles.

Noah Golowich Ankur Moitra Dhruv Rohatgi

Published in: CoRR (2022)

Keyphrases

reinforcement learning
learning systems
online learning
learning algorithm
learning process
neural network
prior knowledge
knowledge base
active learning
dynamic programming
knowledge acquisition
learning styles
learning tasks
positive examples