decision-transformer-dissolves-rl-sequence-modeling-boundary

OUT derived (depth 3)

Created 2026-06-21T14:03:57+00:00 · Reviewed 2026-06-21T15:37:01+00:00

Decision Transformer's recasting of reinforcement learning as sequence modeling dissolves the boundary between RL and sequence prediction — combining with the broader dissolution of classical paradigm boundaries (supervised/unsupervised/RL), this represents a specific mechanism by which the Transformer architecture actively drives paradigm taxonomy dissolution rather than merely being affected by it.

Justifications

SL — Decision Transformer exemplifies a specific dissolution mechanism: one architecture literally absorbing a separate paradigm (RL) into its native modality (sequence modeling).

Antecedents (all must be IN):

IN decision-transformer-rl-as-sequence-modeling — Decision Transformer (Chen et al., 2021) casts reinforcement learning as sequence modeling using the Transformer architecture
IN modern-pipelines-dissolve-classical-paradigm-taxonomy — Modern LLM training pipelines dissolve the classical three-paradigm taxonomy — self-supervised pretraining blurs the supervised/unsupervised boundary (its taxonomic status is actively debated), and the full pipeline synthesizes all three paradigms sequentially, suggesting the taxonomy was always a pedagogical convenience rather than a natural partition of learning.