TensorHouse is a scalable reinforcement learning (RL) platform that focuses on high-throughput experience generation and distributed training. It is designed to efficiently train agents across multiple environments and compute resources. TensorHouse enables flexible experiment management, making it suitable for large-scale RL experiments in both research and applied settings.

Features

  • Supports distributed and parallel RL training across multiple nodes
  • High-throughput experience collection from multiple environments
  • Modular and extensible framework for custom algorithm integration
  • Efficient resource management and task orchestration
  • Includes tools for tracking experiments and analyzing results
  • Compatible with existing RL libraries and custom policies

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow TensorHouse

TensorHouse Web Site

Other Useful Business Software
Veeam Data Platform v13.1 Icon
Veeam Data Platform v13.1

Move workloads across hypervisors and clouds with no vendor lock-in. Try VDP free today.

Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
Try Now
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of TensorHouse!

Additional Project Details

Programming Language

Python

Related Categories

Python Reinforcement Learning Frameworks, Python Reinforcement Learning Libraries, Python Reinforcement Learning Algorithms

Registered

2025-03-13