Acme: A Research Framework for Reinforcement Learning
A library of reinforcement learning components and agents.
reinforcement-learning acme deepmind research code paper library arxiv:2006.00979

Acme is a library of reinforcement learning (RL) agents and agent building blocks. Acme strives to expose simple, efficient, and readable agents, that serve both as reference implementations of popular algorithms and as strong baselines, while still providing enough flexibility to do novel research. The design of Acme also attempts to provide multiple points of entry to the RL problem at differing levels of complexity.

Don't forget to tag @deepmind in your comment, otherwise they may not be notified.

Authors community post
Share this project
Similar projects
Deep Reinforcement Learning for Supply Chain & Price Optimization
Explore how deep reinforcement learning methods can be applied in several basic supply chain and price management scenarios.
Reinforcement Learning Tic Tac Toe with Value Function
A reinforcement learning algorithm for agents to learn the tic-tac-toe, using the value function
Python Implementation of Reinforcement Learning: An Introduction
Plot replications, exercise solutions and Anki flashcards for the entire book by chapters.
Rlx: A modular Deep RL library for research
"rlx" is a Deep RL library written on top of PyTorch & built for educational and research purpose.
Top collections