nathanwispinski/meta-rl
A short conceptual replication of "Prefrontal cortex as a meta-reinforcement learning system" in Jax.
This project explores how a neural network can learn to adapt its behavior to maximize rewards, even after its core learning rules are fixed. It takes in past actions and rewards from a decision-making scenario and produces a new action choice that aims for the best possible outcome. This is ideal for researchers in neuroscience or AI who are studying adaptive learning, reinforcement learning, or the mechanisms of decision-making.
No commits in the last 6 months.
Use this if you are a researcher interested in replicating and understanding how a neural network can learn its own reinforcement learning strategy for tasks like multi-armed bandits.
Not ideal if you need a plug-and-play solution for a real-world business problem or a production-ready adaptive decision-making system.
Stars
18
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nathanwispinski/meta-rl"
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/