Files
foxhunt/crates
jgrusewski b78fd2f1f0 cleanup(fflag): remove enable_q_value_clipping — always clip — [FFLAG-003]
DQNConfig.enable_q_value_clipping was true at all 4 construction sites;
the else branch returned the pre-clamp tensor unchanged (dead identity
path). Q-value clipping is a BUG #37 fix — clipping happens after
forward pass so gradients still flow, and prevents Q-value explosions
from poisoning action selection. Per feedback_no_feature_flags.md, the
flag is gone — clipping is now unconditional. Kept q_value_clip_min /
q_value_clip_max since they're still passed to clamp().
2026-04-20 22:32:08 +02:00
..