jgrusewski 909650f2a1 plan: three-layer stable distributional loss architecture ...

Layer 1: Per-sample C51 loss clamp (MAX_CE=50) breaks PER feedback loop
Layer 2: Label smoothing (ε=0.01) on Bellman target prevents log(0)
Layer 3: IQN primary with fixed τ (QR-DQN style, CUDA Graph compatible)

5 tasks, each independently testable and committable.

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

2026-03-23 20:42:08 +01:00

..

plans

plan: three-layer stable distributional loss architecture

2026-03-23 20:42:08 +01:00

specs

spec: profitability roadmap — 11 findings from deep research

2026-03-23 12:45:06 +01:00