'Indifference' methods for managing agent rewards
Not on the map. Why?
Abstract (arXiv)
`Indifference' refers to a class of methods used to control reward based agents. Indifference techniques aim to achieve one or more of three distinct goals: rewards dependent on certain events (without the agent being motivated to manipulate the probability of those events), effective disbelief (where agents behave as if particular events could never happen), and seamless transition from one reward function to another (with the agent acting as if this change is unanticipated). This paper presents several methods for achieving these goals in the POMDP setting, establishing their uses, strengths, and requirements. These methods of control work even when the implications of the agent's reward are otherwise not fully understood.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Dec 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 1.
4 papers.
- 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 94
- 2023Human Control: Definitions and Algorithmscited by 10
- 2024Towards Shutdownable Agents via Stochastic Choicecited by 2
- 2026Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMscited by 1
- 2026Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs19 Apr 2026
- 2024Towards Shutdownable Agents via Stochastic Choice30 Jun 2024
- 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems10 May 2024
- 2023Human Control: Definitions and Algorithms31 May 2023