CITATION — REFERENCE ENTRY

Toward Idealized Decision Theory — Machine Intelligence Research Institute

Revision 90329f82-1f5a-4bbe-a39b-7743c56c3bb2 · 4/4/2026, 2:52:33 PM UTC

Key: soares2014tdt
Authors: Soares, Nate; Fallenstein, Benja
Issued: 2014
Type: article-journal
Publisher: Machine Intelligence Research Institute
URL: https://arxiv.org/abs/1507.01986

Raw CSL JSON

{
  "URL": "https://arxiv.org/abs/1507.01986",
  "note": "Technical Report 2014-7. Extended version published on arXiv 2015.",
  "type": "article-journal",
  "title": "Toward Idealized Decision Theory",
  "author": [
    {
      "given": "Nate",
      "family": "Soares"
    },
    {
      "given": "Benja",
      "family": "Fallenstein"
    }
  ],
  "issued": {
    "date-parts": [
      [
        2014
      ]
    ]
  },
  "publisher": "Machine Intelligence Research Institute"
}

Claims

fdt-ai-motivation

FDT is motivated in part by the problem of building beneficial AI agents: an AI designed with CDT-style reasoning could be exploited by predictors, while one designed with FDT-style reasoning would behave robustly in a broader range of environments.
tdt-udt-fdt-lineage

Soares and Fallenstein identify TDT as the starting point of the MIRI decision theory research programme, with UDT and FDT representing successive refinements that address limitations in TDT's handling of logical uncertainty and policy-level reasoning.

Available in

en - English