docs(rl): update tutorial with AgenticGRPOLearner for async RL training

Author: AntonyMei

docs/tutorials/posttraining/rl.md

@@ -121,11 +121,25 @@ The overview of what this run will do is as follows:
 
 1. We load a policy model and a reference model. Both are copies of the model
    checkpoint you specified (e.g., `Llama3.1-8b-Instruct`).
-2. Evaluate the policy model's performance on GSM8K math reasoning benchmark.
-3. Train the policy model using GRPO.
-4. Evaluate the policy model's performance on GSM8K math reasoning benchmark
+1. Evaluate the policy model's performance on GSM8K math reasoning benchmark.
+1. Train the policy model using GRPO.
+1. Evaluate the policy model's performance on GSM8K math reasoning benchmark
    after the post-training with GRPO.
 
+By default, the above command will train the model using GRPOLearner from Tunix. To enable
+asynchronous RL training with AgenticGRPOLearner, we can set `rl.use_agentic_rollout` to
+true. An example command will be:
+
+```
+python3 -m maxtext.trainers.post_train.rl.train_rl \
+  model_name=${MODEL?} \
+  load_parameters_path=${MAXTEXT_CKPT_PATH?} \
+  run_name=${RUN_NAME?} \
+  base_output_directory=${BASE_OUTPUT_DIRECTORY?} \
+  chips_per_vm=${CHIPS_PER_VM?} \
+  rl.use_agentic_rollout=True
+```
+
 ## Run GSPO
 
 Run the following command for GSPO:
@@ -144,7 +158,7 @@ The overview of what this run will do is as follows:
 
 1. We load a policy model and a reference model. Both are copies of the model
    checkpoint you specified (e.g., `Llama3.1-8b-Instruct`).
-2. Evaluate the policy model's performance on GSM8K math reasoning benchmark.
-3. Train the policy model using GSPO.
-4. Evaluate the policy model's performance on GSM8K math reasoning benchmark
+1. Evaluate the policy model's performance on GSM8K math reasoning benchmark.
+1. Train the policy model using GSPO.
+1. Evaluate the policy model's performance on GSM8K math reasoning benchmark
    after the post-training with GSPO.