Teleporting Universal Intelligent Agents
نویسنده
چکیده
When advanced AIs begin to choose their own destiny, one decision they will need to make is whether or not to transfer or copy themselves (software and memory) to new hardware devices. For humans this possibility is not (yet) available and so it is not obvious how such a question should be approached. Furthermore, the traditional singleagent reinforcement-learning framework is not adequate for exploring such questions, and so we base our analysis on the “multi-slot” framework introduced in a companion paper. In the present paper we attempt to understand what an AI with unlimited computational capacity might choose if presented with the option to transfer or copy itself to another machine. We consider two rigorously executed formal thought experiments deeply related to issues of personal identity: one where the agent must choose whether to be copied into a second location (called a “slot”), and another where the agent must make this choice when, after both copies exist, one of them will be deleted. These decisions depend on what the agents believe their futures will be, which in turn depends on the definition of their value function, and we provide formal results.
منابع مشابه
Design and Simulation of a 100 kVA Intelligent Universal Transformer Enjoying the Voltage Ratio of 20kv:380v
In order to reduce the volume and size of distribution power transformer, precise and extended controlling of transformer output, the conventional transformers are replaced by intelligent universal transformers (IUTs). In this paper, an IUT, typical of Iran national grid, with the voltage ratio of 20kV:380 V is designed and simulated. Regarding the IUT implementation, a cascaded H-bridge invert...
متن کاملTeleporting in an X Window System Environment
Teleporting is the ability to redirect a windowing environment to different computer displays. This paper describes the implementation of a teleporting system developed at Olivetti Research Laboratory (ORL). We outline two particular features of the system that make it powerful. First, it operates with existing applications, which will run without any modification. Second, it incorporates sophi...
متن کاملA Context-aware Architecture for Mental Model Sharing through Semantic Movement in Intelligent Agents
Recent studies in multi-agent systems are paying increasingly more attention to the paradigm of designing intelligent agents with human inspired concepts. One of the main cognitive concepts driving the core of many recent approaches in multi agent systems is shared mental models. In this paper, we propose an architecture for sharing mental models based on a new concept called semantic movement....
متن کاملTowards an Adaptive Intelligent Agent
We consider the learning required for existing intelligent biological agents (human and animal), and partition the learning required to produce such an agent into: (i) genomic, (ii) cultural, and (iii) individual learning. Using this simple taxonomy we consider limits inherent on the complexity of genomic knowledge, and the fact that many complex tasks did not exist during evolutionary times. B...
متن کامل