Skip to content

v2-io/paper-unified-convergence-rl

Repository files navigation

Unified Convergence Theory for Non-Stationary RL — paper repository

A four-strand composition for cumulative dynamic regret in non-stationary reinforcement learning. Single-author theory paper. Two-Gap diagnostic separating goal-feasibility from policy-quality; point-mass reverse-KL/TV identity strictly improving Pinsker and Bretagnolle–Huber at the deterministic-π* corner; strategic tempo with forgetting prerequisite as structural survival inequality; loop-as-causal-engine for learnable bounds. Cumulative dynamic regret rate $O(\sqrt{B_T \cdot T})$.

Repository follows the segmented-paper workflow: paper segments live in src/, with one or more OUT.*.md concatenation manifests assembling them into output forms (e.g. OUT.full-paper.md for the unconstrained version, OUT.neurips-2026-paper.md for the 9-page-budget submission). Currently bootstrapping the segmented layout.

Consumed as a submodule by an umbrella workspace.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages