foxhunt

Files

jgrusewski dd049d9a4c fix(rl): reward clamp bootstrap WIN=1.0 LOSS=3.0 (was 0.5/0.5)

The clamp bounds were bootstrapped at ±0.5 (matching the old ±0.5 atom
span) instead of the intended asymmetric WIN=1.0, LOSS=3.0. This
caused: (1) apply_reward_scale clamped at ±0.5 instead of [-3,+1],
(2) the C51 atom span EWMA target = max(1.0, 0.5) = 1.0 → V_MIN
never moved because target min(-1.0, -0.5) = -1.0 = bootstrap.

Now: WIN=1.0 (positive reward ceiling), LOSS=3.0 (loss-aversion
asymmetry per pearl_audit_unboundedness). Atom span will EWMA from
[-1, +1] toward [-3, +1] over ~2100 steps (α=0.001).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-27 15:46:59 +02:00

cuda

feat(cuda): re-enable C51 atom span EWMA anchored on clamp bounds

2026-05-27 15:04:20 +02:00

examples

fix(cuda): SAC co-tuning reads ACTION entropy, not policy entropy

2026-05-27 13:44:10 +02:00

src

fix(rl): reward clamp bootstrap WIN=1.0 LOSS=3.0 (was 0.5/0.5)

2026-05-27 15:46:59 +02:00

tests

perf(rl): fuse adamw_increment into adamw_step + tau into iqn_forward