Our library for RL environments + evals
Appears on
Quick read
Latest capture 2026-08-02 03:14
4 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 2
Claude Code 2
6 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +291
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Agentic RL Training at Scale
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Simple RL training for reasoning
No description.
Evaluate and improve models and agents using environments
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
