SafeRL-Lab/BenchNetRL
🔥Benchmarking of Neural Network Architectures in Reinforcement Learning.
This tool helps machine learning engineers and researchers evaluate how different neural network architectures perform within reinforcement learning tasks. You input various neural network designs and benchmark environments (like Atari games or robotics simulations), and it outputs detailed performance metrics such as steps per second, training time, and GPU memory usage. This allows you to identify the most efficient and effective network for your specific RL problem.
Use this if you need to systematically compare the speed and resource efficiency of different neural network architectures (like LSTMs, Transformers, or Mamba) when training reinforcement learning agents.
Not ideal if you are looking for a simple, out-of-the-box solution to train an RL agent without needing to dive deep into architectural comparisons.
Stars
34
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jan 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SafeRL-Lab/BenchNetRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
opentensor/bittensor
Internet-scale Neural Networks
trailofbits/fickling
A Python pickling decompiler and static analyzer
benchopt/benchopt
A framework for reproducible, comparable benchmarks
BiomedSciAI/fuse-med-ml
A python framework accelerating ML based discovery in the medical field by encouraging code...
mosaicml/streaming
A Data Streaming Library for Efficient Neural Network Training