AIPython★ 568⑂ 35 forksApache-2.0
zli12321/LHTB
LHTB LONG-TERM BENCHMARK TEST
A long-horizon terminal benchmark with dense reward evaluation for training agents.
// KEY FEATURES
- Dense reward system for training long trajectories
- Support for multi-task scenarios in terminal environments
- Easy integration with RLlib and Stable-Baselines3
#claude#deepseek-v4-pro#fable5#glm-52#gpt-56-sol#grok-45#hy3#kimi-k3#long-horizon-agents#long-horizon-tasks#long-horizon-terminal-bench#minimax
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram