foxhunt

Files

jgrusewski 2f8fa1ab19 Merge feature/action-diversity-fix: DQN hyperopt overhaul (B1-B3, C1-C4)

7 root cause fixes for DQN hyperopt train/eval mismatch and reward corruption:
- B1: Eval mode (noisy noise disabled, softmax action selection)
- B3: Per-bar portfolio state sync in eval
- C1: Extrinsic-only replay buffer (curiosity removed from rewards)
- C2: Single exploration (noisy nets only, no epsilon/count bonus on Q-values)
- C3: Neutral hold reward, search space 31D to 30D
- C4: Sharpe-based early stopping (replaces val-loss plateau)

2720 tests, 0 failures, 0 clippy warnings.

2026-03-06 11:44:39 +01:00

backtesting

docs: create/update README.md for all 17 crates

2026-03-01 22:47:39 +01:00

common

fix(metrics): push training metrics to pushgateway before pod exit

2026-03-06 00:32:09 +01:00

config

refactor: rename JWT issuer foxhunt-api-gateway → foxhunt-api, drop compat aliases

2026-03-05 00:22:04 +01:00

ctrader-openapi

docs: create/update README.md for all 17 crates