rl-suboptimality-bias-overfitting-decomposition

IN premise — entries/2026/06/21/wiki-BiasE28093variance_tradeoff-chunk-3.md

Created 2026-06-21T09:55:49+00:00

In reinforcement learning, suboptimality decomposes into asymptotic bias (algorithm-dependent) and overfitting (data-dependent), analogous to the classical bias-variance tradeoff.

Dependents

These beliefs depend on this one:

• IN ml-error-decomposition-universal-principle — Error decomposition into irreducible and reducible components appears as a recurring structural pattern across ML paradigms — supervised learning decomposes prediction error into bias + variance + irreducible noise, while reinforcement learning independently decomposes suboptimality into asymptotic bias + overfitting. This parallel suggests that separating what-can-be-learned from what-cannot may be a common structural feature of learning problems, though evidence from only two paradigms is insufficient to establish it as a universal invariant of learning itself.