wladekpal/golden-standard

Is Temporal Difference Learning the Gold Standard for Stitching in RL? Code repository for research paper.

35
/ 100
Emerging

This project helps evaluate how well different reinforcement learning (RL) algorithms can "stitch" together short training experiences to solve longer, more complex tasks. It takes in configurations for RL algorithms and an environment (like moving boxes in a grid) and outputs performance metrics and visualizations showing whether the algorithm successfully learns to complete the task. This tool is for RL researchers or practitioners focused on developing or benchmarking new foundational RL models.

Use this if you are a reinforcement learning researcher evaluating the 'stitching' capabilities of different goal-conditioned RL algorithms, especially in varying complexities of tasks.

Not ideal if you are looking for a general-purpose RL library to train agents for real-world applications or production environments.

reinforcement-learning machine-learning-research AI-model-evaluation sequential-decision-making
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Jupyter Notebook

License

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wladekpal/golden-standard"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.