Space-Time Embedded Intelligence

By Laurent Orseau, Mark B. Ring. 2012

61 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Robotics & Control

Citations in the corpus

Scalable agent alignment via reward modeling: a research direction (2018, background): “In particular, many of their problems aim to address perceived difﬁculties in applying current notions of optimal behavior to agents which are part of their environment (Orseau & Ring, 2012) and thus may not remain cleanly delineated from it (Demski & Garrabrant, 2018).”
Research Priorities for Robust and Beneficial Artificial Intelligence (2015, background): “…correlations between AI systems’ behaviors and those of their environments or of other agents [60–64], how agents that are embedded in their environments should reason [65, 66], and how to reason about uncertainty over logical consequences of beliefs or other deterministic computations [67].”
AI Safety Gridworlds (2017, background): “However, this assumption does not hold in the real world, where the agent is a program that runs on an actual computer, which itself is part of the environment (Orseau and Ring, 2012; Everitt et al., 2015).”
AGI Safety Literature Review (2018, unknown): “Section 2.1). Extensions of this framework have been developed for studying goal alignment (Everitt and Hutter, 2018a), multi-agent interaction (Leike, Taylor, et al., 2016), space-time embeddedness (Orseau and Ring, 2012), self-modication (Everitt, Filan, et al., 2016; Orseau and Ring, 2011), obser”
Self-Modification of Policy and Utility Function in Rational Agents (2016, methodology): “See Orseau and Ring (2012) for a model where the environment can change the agent.”
Information-Theoretic Bounded Rationality (2015, background): “Another recent approach to model bounded resources with profound implications is space-time embedded intelligence in which agents are treated as local computation patterns within a global computation of the world [Orseau and Ring, 2012].”
Reward is enough (2021, background): “Bounded [50,43,36] or computational rationality [27] suggests that agents should select the program that best achieves their goals, given the real-time consequences arising from that program (for example, how long the program takes to execute), and subject to limitations on the set of programs (for ”
Embedded Agency (2019, background): “Orseau and Ring (2012) provide a way of thinking about this in “Space-Time Embedded Intelligence”.”
Formalizing Convergent Instrumental Goals (2016, background): “It is not entirely clear how to extend the model in such a fashion at this time, but the “space-time embedded intelligence” model of Orseau and Ring [20] and the “reflective oracle” framework of Fallenstein, Taylor, and Christiano [21] both offer plausible starting points.”
Formalizing Two Problems of Realistic World-Models (2015, background): “Orseau and Ring (2012) give a characterization of the problem which humans face, in implementing a space-time embedded agent, but their problem description requires that we provide a distribution ρ which already characterizes our beliefs about the environment, and so sheds little light on questions…”