This is the Linux app named Scalable Distributed Deep-RL whose latest release can be downloaded as scalable_agentsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Scalable Distributed Deep-RL with OnWorks for free.
Следуйте этим инструкциям, чтобы запустить это приложение:
- 1. Загрузил это приложение на свой компьютер.
- 2. Введите в нашем файловом менеджере https://www.onworks.net/myfiles.php?username=XXXXX с желаемым именем пользователя.
- 3. Загрузите это приложение в такой файловый менеджер.
- 4. Запустите онлайн-эмулятор OnWorks Linux или Windows или онлайн-эмулятор MACOS с этого веб-сайта.
- 5. В только что запущенной ОС OnWorks Linux перейдите в наш файловый менеджер https://www.onworks.net/myfiles.php?username=XXXXX с желаемым именем пользователя.
- 6. Скачайте приложение, установите его и запустите.
СКРИНШОТЫ
Ad
Масштабируемое распределенное глубокое обучение
ОПИСАНИЕ
Scalable Agent is the open implementation of IMPALA (Importance Weighted Actor-Learner Architectures), a highly scalable distributed reinforcement learning framework developed by Google DeepMind. IMPALA introduced a new paradigm for efficiently training agents across large-scale environments by decoupling acting and learning processes. In this architecture, multiple actor processes interact with their environments in parallel to collect trajectories, which are then asynchronously sent to a centralized learner for policy updates. The learner uses importance weighting to correct for policy lag between actors and the learner, enabling stable off-policy training at scale. This design allows the system to scale efficiently to hundreds of environments and billions of frames while maintaining sample efficiency and stability. The implementation supports training in DeepMind Lab (DMLab) and has also been adapted for other environments like Atari and Street View.
Особенности
- Implements IMPALA, a scalable distributed deep reinforcement learning framework
- Supports asynchronous actor-learner architecture with importance weighting
- Efficiently trains agents on large-scale environments (e.g., DMLab-30, Atari)
- Includes dynamic batching for optimized data throughput
- Compatible with DeepMind Sonnet and TensorFlow
- Provides Dockerfile setup for reproducible single-machine or distributed training
Язык программирования
C ++, Python
Категории
This is an application that can also be fetched from https://sourceforge.net/projects/scalable-dist-deep-rl.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
