wladekpal/golden-standard
Is Temporal Difference Learning the Gold Standard for Stitching in RL? Code repository for research paper.
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.
Stars
10
Forks
2
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/