jgrusewski c94af7523e docs: Phase 2 hierarchical 4-branch DQN spec — direction(3) × magnitude(3) × order(3) × urgency(3) ...

Replaces broken 9-output exposure branch with two 3-output branches.
Each 3-output branch has -1/2 gradient (33%) — strong enough for dueling.
Eliminates i%3 Q-value degeneracy permanently.

3 novel gems: direction-specific dense reward, per-branch epsilon,
Flat detection shortcut with gradient zeroing.

~480 lines of dead code removed (aux optimizer, CEA, pre-training).
20+ files changed. Full CUDA, no CPU path, no stubs.

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

2026-04-08 12:04:23 +02:00

..

plans

fix: aux GEMM gradient explosion — scale 0.5→0.01 + clip after backward

2026-04-08 10:03:54 +02:00

specs

docs: Phase 2 hierarchical 4-branch DQN spec — direction(3) × magnitude(3) × order(3) × urgency(3)

2026-04-08 12:04:23 +02:00