Small docs fixes (#336)

Signed-off-by: Brian Yu <bxyu@nvidia.com>

Author: bxyu-nvidia

docs/tutorials/index.md

@@ -24,4 +24,12 @@ Transform rollouts into training data for supervised fine-tuning (SFT) and direc
 {bdg-secondary}`sft` {bdg-secondary}`dpo`
 :::
 
+:::{grid-item-card} {octicon}`workflow;1.5em;sd-mr-1` RL Training with NeMo RL
+:link: rl-training-with-nemo-rl
+:link-type: doc
+Train a model with NeMo RL. Learn how to set up NeMo Gym + NeMo RL training environment, run tests, prepare data, and launch single and multi-node training runs.
++++
+{bdg-secondary}`sft` {bdg-secondary}`dpo`
+:::
+
 ::::

docs/tutorials/offline-training-w-rollouts.md

@@ -352,10 +352,3 @@ You now know how to transform rollouts into training data:
 - **Quality filtering and curation** techniques  
 - **Evaluation methods** to measure improvement
 - **Best practices** for sustainable offline training workflows
-
-**Next steps**: 
-<!-- TODO: Add link [Online Training with Rollouts (RL)](07-online-training.md) -->
-<!-- - **Online Training with Rollouts (RL) (Coming soon!)** - Learn real-time training approaches -->
-<!-- TODO: Add link [Building Custom Resource Servers](08-building-custom-resources.md) -->
-<!-- - **Building Custom Resource Servers (Coming soon!)** - Create domain-specific training data -->
-- **[Configuration Management]**

docs/tutorials/rl-training-with-nemo-rl.md

@@ -1,3 +1,5 @@
+(rl-training-with-nemo-rl)=
+
 # RL Training with NeMo RL
 
 **Goal**: Train a model with NeMo RL. Learn how to set up NeMo Gym + NeMo RL training environment, run tests, prepare data, and launch single and multi-node training runs!