dopamine
RL framework
A research framework for fast prototyping of reinforcement learning algorithms.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
11k stars
424 watching
1k forks
Language: Jupyter Notebook
last commit: almost 2 years agoLinked from 5 awesome lists
aigooglemlrltensorflow
ethicalml/awesome-production-machine-learning
ly0n/awesome-robotic-tooling
krzjoa/awesome-python-data-science
tigerneil/awesome-deep-rl
zslucky/awesome-ai-booksRelated projects:
| Repository | Description | Stars |
|---|---|---|
 google-deepmind/lab | A 3D environment for testing and training artificial intelligence agents | 7,146 |
| google-deepmind/jaxline | Provides a Python-based framework for building distributed JAX training and evaluation experiments | 153 |
| google-deepmind/dm_control | A software stack for simulating physics-based environments and training reinforcement learning agents | 3,849 |
| google-deepmind/deepmind-research | Provides implementations and illustrative code to accompany DeepMind research publications | 13,329 |
| google/trax | An end-to-end deep learning library with clear code and speed | 8,114 |
 janhuenermann/neurojs | A JavaScript framework for building and training neural networks in the browser | 4,400 |
 opendilab/di-engine | A comprehensive decision intelligence framework for building and deploying reinforcement learning models | 3,143 |
| google-deepmind/acme | A toolkit for building and deploying reinforcement learning agents | 3,542 |
 facebookresearch/reagent | An end-to-end platform for applied reinforcement learning developed at Facebook. | 3,575 |
 farama-foundation/gymnasium | Develops and compares reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments | 7,613 |
| google/jaxopt | An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning. | 941 |
| google/flax | Provides a flexible neural network library and ecosystem for JAX | 6,196 |
 microsoft/qlib | An AI-oriented quantitative investment platform that supports machine learning modeling and automated trading. | 15,767 |
 devsisters/dqn-tensorflow | An implementation of a deep reinforcement learning algorithm for human-level control in game environments using TensorFlow. | 2,491 |
 deepjavalibrary/djl | A high-level Java framework for building and deploying deep learning models | 4,204 |