Primer
  • Factored Cognition Primer
  • Intro
    • Factored Cognition
    • Before We Start
  • Chapters
    • Hello World
    • Question Answering
      • Q&A without context
      • Q&A about short texts
    • Debate
      • Representing debates
      • From debates to prompts
      • The debate recipe
    • Long Texts
      • Loading paper text
      • Finding relevant paragraphs
      • Answering given paragraphs
    • Amplification
      • Asking subquestions
      • Answering subquestions
      • One-step amplification
      • Recursive amplification
    • Verifiers
      • Checking answers
      • Checking reasoning steps
    • Tool Use
      • Web search
      • Interpreters
    • Deduction
      • Chain of Thought
    • Action Selection
      • One-shot action selection
      • Iterative action selection
    • Amplification Revisited
  • Appendix
    • What’s next?
  • Links
    • We’re Hiring
    • Our Slack Community
    • ICE on Github
Powered by GitBook
On this page
Edit on GitHub
  1. Chapters
  2. Action Selection

Iterative action selection

Choosing a sequence of actions

PreviousOne-shot action selectionNextAmplification Revisited

Last updated 2 years ago

For non-trivial questions it’s generally not enough to take a single cognitive action. For example, consider:

What is the log10 of the number of people living in the US vs China?

Ideally we’d first look up the populations, then compute the logarithms.

Alas, this chapter hasn’t been written yet.

Exercise

Implement iterative action selection. If you need inspiration, take a look at this execution trace:

Get feedback on exercise solutions

For even more inspiration, take a look at in the ICE repository.

If you want feedback on your exercise solutions, submit them through . We—the team at Ought—are happy to give our quick take on whether you missed any interesting ideas.

sequential_action.py
this form
Execution trace ()
view online