jrcalgo/RelayRL-prototype

Unstable Single-Agent Distributed Reinforcement Learning Framework written in Rust & exported to Python

1 stars 0 forks 0 watchers Rust

client-server distributed-ml python-bindings pytorch reinforcement-learning tch-rs

View on GitHub

1 Open Issue Need Help Last updated: Jul 2, 2025

Open Issues Need Help

View All on GitHub

Add more policy gradient algorithms (PPO, RPO, DDPG, TD3, etc.) 2 months ago

AI Summary: Implement several popular policy gradient algorithms (PPO, RPO, DDPG, TD3) within the existing RelayRL distributed reinforcement learning framework, ensuring modularity and compatibility with the framework's design patterns. This involves writing the algorithm implementations in Python, integrating them with the existing Rust backend, and adding appropriate tests and documentation.

Complexity: 4/5

enhancement good first issue

jrcalgo/RelayRL-prototype

Unstable Single-Agent Distributed Reinforcement Learning Framework written in Rust & exported to Python

Rust

#client-server#distributed-ml#python-bindings#pytorch#reinforcement-learning#tch-rs