Repository navigation
MTRL: Add end-to-end MTRL SOP-Bench example (AgentCore) - #6532
Open
SapanaChaudhary wants to merge 2 commits into
Open
SapanaChaudhary wants to merge 2 commits into
SapanaChaudhary wants to merge 2 commits into
Conversation
Add v3-examples/model-customization-examples/serverless/mtrl/, a complete, runnable multi-turn RL example: fine-tune openai-reasoning-gpt-oss-20b on the SOP-Bench aircraft_inspection task with a rollout agent on Amazon Bedrock AgentCore. - 01_build_and_deploy_agent.ipynb: task, tools, reward design (and the reward hack it prevents), AgentCore deploy - 02_train.ipynb: prompt dataset, MultiTurnRLTrainer GRPO run, reading MLflow metrics and traces - 03_evaluate_and_deploy.ipynb: MultiTurnRLEvaluator base vs. fine-tuned, failure diagnosis, deployment options, scoped cleanup - sopbench_agent/: the agent package (entrypoint, agent loop, tools, reward), Dockerfile, and scripts - prerequisites.yaml: IAM roles, S3 bucket, MLflow app (or an existing one), and managed policies for the notebook identity
SapanaChaudhary
had a problem deploying
to
manual-approval
October 23, 2026 18:29 — with 
GitHub Actions
Error
GitHub Actions
Error
mufaddal-rohawala
approved these changes
Oct 23, 2026
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
[Add v3-examples/model-customization-examples/serverless/mtrl/, a complete, runnable multi-turn RL example: fine-tune openai-reasoning-gpt-oss-20b on the SOP-Bench aircraft_inspection task with a rollout agent on Amazon Bedrock AgentCore.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.
](https://github.com/aws/sagemaker-python-sdk/compare/master...SapanaChaudhary:sagemaker-python-sdk:documentation/mtrl-sopbench-example?expand=1)