Consistent Aggregation of Objectives with Diverse Time Preferences
Requires Non-Markovian Rewards

Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards

30 September 2023

Silviu Pitis

Papers citing "Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards"

5 / 5 papers shown

Title
Pluralistic Alignment Over Time Toryn Q. Klassen P. A. Alamdari Sheila A. McIlraith 26 4 0 16 Nov 2024
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning Sarah Rathnam S. Parbhoo Weiwei Pan Susan A. Murphy Finale Doshi-Velez OffRL 9 4 0 20 Jun 2023
Reinforcement Learning with Non-Exponential Discounting M. Schultheis Constantin Rothkopf Heinz Koeppl 14 11 0 27 Sep 2022
Utility Theory for Sequential Decision Making Mehran Shakerinava Siamak Ravanbakhsh 22 7 0 27 Jun 2022
Reinforcement Learning with Non-Markovian Rewards Maor Gaon Ronen I. Brafman OffRL 22 75 0 05 Dec 2019