Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods
By Jiale Zhi, Rui Wang, Jeff Clune, Kenneth O. Stanley. 2020
12 citations recorded by the source corpus.
Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the underlying distributed computing frameworks. These challenges include frequent interaction with simulations, the need for dynamic scaling, and the need for a user interface with low adoption cost and consistency across different backends. In this paper we address these challenges while still retaining development efficiency and flexibility for both research and practical applications by introducing Fiber, a scalable distributed computing framework for RL and population-based methods. Fiber aims to significantly expand the accessibility of large-scale parallel computation to users of otherwise complicated RL and population-based approaches without the need to for specialized computational expertise.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Jeff Clune
- Pieter Abbeel
- Kenneth O. Stanley
- Joel Lehman
- Quoc V. Le
- Yoshua Bengio
- Chelsea Finn
Citations in the corpus
- Acme: A Research Framework for Distributed Reinforcement Learning (2020, methodology): “Fiber (Zhi et al., 2020) and Ray (Moritz et al., 2017) are both generic tools for expressing distributed computations, similar to Launchpad, described below.”
- Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions (2020, methodology): “The implementation is based on Fiber (Zhi et al., 2020), a recently released distributed computing library in Python that enables seamless parallelization over any number of cores.”