diff --git a/infra/k8s/argo/train-dqn-template.yaml b/infra/k8s/argo/train-dqn-template.yaml
index 7444439e1..7885f1560 100644
--- a/infra/k8s/argo/train-dqn-template.yaml
+++ b/infra/k8s/argo/train-dqn-template.yaml
@@ -41,11 +41,11 @@ spec:
       - name: gpu-pool
         value: ci-training-h100
       - name: hyperopt-trials
-        value: "30"          # 28D param space needs more exploration
+        value: "50"          # 24D param space needs full exploration
       - name: hyperopt-epochs
-        value: "8"
+        value: "20"          # 20 epochs per trial with early stopping
       - name: train-epochs
-        value: "80"           # DQN benefits from longer training
+        value: "200"          # matches dqn-production.toml
       - name: symbol
         value: ES.FUT
       - name: data-dir
diff --git a/infra/k8s/argo/training-workflow-template.yaml b/infra/k8s/argo/training-workflow-template.yaml
index 16918e1bb..680b9aaee 100644
--- a/infra/k8s/argo/training-workflow-template.yaml
+++ b/infra/k8s/argo/training-workflow-template.yaml
@@ -338,7 +338,7 @@ spec:
               --mbp10-data-dir {{workflow.parameters.mbp10-data-dir}} \
               --trades-data-dir {{workflow.parameters.trades-data-dir}} \
               --output-dir /workspace/output \
-              --max-steps-per-epoch {{workflow.parameters.train-epochs}} \
+              --epochs {{workflow.parameters.train-epochs}} \
               $HYPEROPT_FLAG \
               --ensemble-top-k {{workflow.parameters.ensemble-top-k}}
 
@@ -349,6 +349,8 @@ spec:
             value: info
           - name: SQLX_OFFLINE
             value: "true"
+          - name: FOXHUNT_TRAINING_PROFILE
+            value: /workspace/config/training/dqn-production.toml
           - name: OTEL_EXPORTER_OTLP_ENDPOINT
             value: "http://tempo.foxhunt.svc.cluster.local:4317"
           - name: CUBLAS_WORKSPACE_CONFIG