SirStone 96065597c0 fix(divergence): guard reward-normalizer cold start; drop arctanh recovery ...

Welford variance-collapse divided by 1e-8 producing bit-exact +/−5e8 /
+−1.25e8 poisoned rewards into TD targets; guard skips normalization
until stats meaningful; tanh-inversion removal bounds log-prob path.

Fixes #60.

2026-08-24 01:03:04 +02:00

..

SAC_LSTM_Bot

fix(divergence): guard reward-normalizer cold start; drop arctanh recovery

2026-08-24 01:03:04 +02:00

SAC_LSTM_Bot.json

feat(SAC_LSTM_Bot): training harness (#49)

2026-08-21 21:51:27 +02:00

SAC_LSTM_Bot.nim

feat(SAC_LSTM_Bot): campaign v2 levers — aggression/anti-ram reward shaping + stability knob overrides (part 2)

2026-08-22 19:44:58 +02:00