Stem undiscount$ (all stems)

2 papers:

ICML-2015-LakshmananOR #bound #learning

Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning (KL, RO, DR), pp. 524–532.

ICML-1993-Schwartz #learning

A Reinforcement Learning Method for Maximizing Undiscounted Rewards (AS), pp. 298–305.