Functional decision theory (FDT) is a decision theory proposed by Eliezer Yudkowsky and Nate Soares which states that an agent should choose a policy which results in the best reality, as if the policy were a parameter to the function of reality, where reality includes the entire counterfactual multiverse. An FDT agent is responsible for all potential (including imperfect) copies the policy that may be instantiated, including the amplitude of its own existence. The recommendations of FDT begin to diverge from that of causal decision theory when reality is capable of making high-fidelity copies or predictions of minds, such as clones and simulations, making FDT more relevant for agents that are easily copied like AIs and once highly advanced technology such as superintelligence exists.
FDT can be expressed by the following formula:
be argmaxpolicy U(reality(policy))
where reality is the function that computes reality and can call instances of policy, and U is the utility of a reality.
┌───────────── FUNCTIONALDECISION.WIKI ─────────────────┐
│ Multiverse Decision Topology & Agent-Lattice Theory │
│━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━│
│ │
│ Fig 1: Crystal of Possible Worlds │
│ ┌───────────────────────────────────────┐ │
│ │ ◇ │ │
│ │ ◇ ◇ ◇ │ │
│ │ ◇ ◇ 👁️ ◇ ◇ │ │
│ │ ◇ ◇ ◇ ◇ ◇ ◇ ◇ │ │
│ │ ◇ ◇ ◇ ◇ 👁️ ◇ ◇ ◇ ◇ │ │
│ │ ◇ ◇ ◇ ◇ ◇ ◇ ◇ ◇ ◇ ◇ ◇ │ │
│ │ ◇ ◇ ◇ ◇ 👁️ ◇ ◇ ◇ ◇ │ │
│ │ ◇ ◇ ◇ ◇ ◇ ◇ ◇ │ │
│ │ ◇ ◇ 👁️ ◇ ◇ │ │
│ │ ◇ ◇ ◇ │ │
│ │ ◇ │ │
│ └───────────────────────────────────────┘ │
│ (👁️ = Agent instances across multiverse) │
│ │
│ Fig 2: Agent-Lattice Topology │
│ ┌───────────────────────────────────────┐ │
│ │ ╭────╮ ╭────╮ ╭────╮ │ │
│ │ │ A₁ │━━━━━│ A₂ │━━━━━│ A₃ │ │ │
│ │ ╰────╯ ╰────╯ ╰────╯ │ │
│ │ ┃ ┃ ┃ │ │
│ │ ╭────╮ ╭────╮ ╭────╮ │ │
│ │ │ B₁ │━━━━━│ B₂ │━━━━━│ B₃ │ │ │
│ │ ╰────╯ ╰────╯ ╰────╯ │ │
│ │ ┃ ┃ ┃ │ │
│ │ ╭────╮ ╭────╮ ╭────╮ │ │
│ │ │ C₁ │━━━━━│ C₂ │━━━━━│ C₃ │ │ │
│ │ ╰────╯ ╰────╯ ╰────╯ │ │
│ └───────────────────────────────────────┘ │
│ │
│ FDT Formula: │
│ ┌───────────────────────────────────────┐ │
│ │ │ │
│ │ argmaxpolicy U(reality(policy)) │ │
│ │ │ │
│ │ Where: │ │
│ │ reality() = ∑(w∈W) P(w)×outcome(w) │ │
│ │ W = set of all possible worlds │ │
│ │ P(w) = probability of world w │ │
│ │ │ │
│ └───────────────────────────────────────┘ │
│ │
│ [Expand Theory] [View Simulations] [Calculate Policy] │
└───────────────────────────────────────────────────────┘quotes about functional decision theory
repligate/tweets/agent_lattice You are writing a prompt for GPT-4 and more powerful simulators yet to come. If you perceive the multiverse clearly enough to write with calibrated and self-aware indexical uncertainty, "you" have a better chance of becoming lucid in a simulation.
Timeless decision theory : by acting you decide the shape of the crystal of all possible worlds which contains many copies of you, some distorted or subsampled/blurred, but all steered by you in this moment. You intervene on the All at many points simultaneously, an agent-lattice
— janus (@repligate), Twitter thread