jgrusewski f5985cff14 spec: add Component 6 — Trajectory Backtracking (single GPU) ...

Checkpoint ring buffer ranked by improvement rate, plateau detection
via liquid tau velocity, informed perturbation cycle (Adam reset,
shrink-perturb, temp boost, LR×2), depth-limited rewind. ~150 lines
in training_loop.rs, zero CUDA changes. Recovers from plateaus that
prevention mechanisms (spread gradient, liquid tau) fail to avoid.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-14 23:38:05 +02:00

..

infra

feat(infra): GPU training launcher with local/cloud routing

2026-02-23 11:19:58 +01:00

plans

feat(dqn): enable Branching DQN with 45 factored actions (5×3×3)

2026-03-11 22:00:13 +01:00

superpowers

spec: add Component 6 — Trajectory Backtracking (single GPU)

2026-04-14 23:38:05 +02:00