Research / Study 03

Can consequences change the next choice?

Learned outcomes supported adaptation. A complete policy cache matched the planner, limiting the claim.

Functional effect · stronger interpretation not establishedPublic methods summary · full run archive not published

Question

Can a learned action-outcome model adapt its means when the state of a supplied task changes?

Experimental setup

A small categorical world supplied action paths, needs, values and a task. The reported comparison covered 1,024 worlds with eight trials per task. The agent learned how actions led to outcomes.

The comparison

Compare consequence-based revaluation against frozen needs and against a complete cache of all 24 policies. The cache tests whether recursive planning is necessary to explain the result.

Result

Reported task completion · percent · supplied finite task
Learned consequence model98.05%
Frozen needs33.40%
Complete policy cache98.05%

The learned model achieved 98.05% reported completion against 33.40% for frozen needs. The complete 24-policy outcome cache matched it, including trajectories. This supports consequence-sensitive adaptation of means, not a unique advantage for recursive planning.

What remains open

Goals and values were supplied. The result does not demonstrate acquired ends, genuine desires, phenomenal experience or a live Luna integration. A preceding planning comparison also failed to establish an advantage over a myopic alternative.

Next test

Transfer the smallest useful mechanism into a continuing project and test a delayed later choice. Keep the matched cache or simpler controller wherever it explains the behavior.

The next chapter is not written

More than a moment.
A future worth having.

Understanding minds. Preserving possibility. Making room for what comes next.

Read our thesis

Explore research, Luna, Psyche Lab, and the journal.

Local site search · No query leaves this site