Merge pull request #25 from lvbaocheng/feature/gate-soft-metric

Add configurable gate metric (hard / soft / mixed) for skill validation

Default is `hard`, preserving exact pre-PR behavior — verified by 22 unit
assertions on the gate module plus an end-to-end 8-step trainer-trajectory
test that produces a bit-for-bit identical accept/reject sequence between
the pre-PR and post-PR code paths under `gate_metric: hard`. Paper-
reproduction results are unaffected.

`soft` and `mixed` are opt-in via `evaluation.gate_metric` in the config
and address small-selection-set runs where discrete hard accuracy is too
coarse to distinguish candidate skills.

configs/_base_/default.yaml

@@ -71,6 +71,12 @@ optimizer:
 
 evaluation:
   use_gate: true
+  # gate_metric: 'hard' (default, backward-compatible),
+  #              'soft' (use soft/F1 score),
+  #              'mixed' ((1 - w) * hard + w * soft).
+  # See skillopt/evaluation/gate.py for details.
+  gate_metric: hard
+  gate_mixed_weight: 0.5
   sel_env_num: 0
   test_env_num: 0
   eval_test: true