# yifanzhang-pro/KLPO > KLPO is a critic-free, single-rollout reinforcement learning method for training agentic language models, using token regression and Monte Carlo KL estimation instead of value models or response groups. It provides the loss implementation, CPU tests, and a native Molt training integration. - Magnitude: 0.0 out of 10 — Quiet - Stars: 182 total · Not enough measurements today - Star trust: star growth looks organic - Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-19 · Last push: 2026-09-21 - GitHub: https://github.com/yifanzhang-pro/KLPO · Homepage: https://yifanzhang-pro.github.io/KLPO/ · Page: https://gitnova.dev/en/r/yifanzhang-pro/KLPO ## Useful for - Train an agentic LLM with KLPO loss using the provided Molt launcher - Run the CPU toy example to verify all eight route/estimator combinations - Compare MC-KL, TopK-KL, Binary KL and Full KL estimators on a small policy ## How to get started ```sh git clone https://github.com/yifanzhang-pro/KLPO.git cd KLPO python -m venv .venv source .venv/bin/activate pip install -e '.[test]' python examples/train_toy.py # Default: token regression + MC-KL, M=128 python examples/train_toy.py --mc-samples 1 python -m pytest -q ``` Copied as is from the “quick start” section of the README. GitNova has not run these commands: check them in the original before running: https://github.com/yifanzhang-pro/KLPO#readme ## Why it’s here - There are not enough fresh counter measurements for today's UTC day. The gain is unknown. - The repository is 16 days old and already has 182 stars. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 16 - Issues and pull requests: 1 - Watchers: 2 - Average over the last week: 0 per day - Usual pace: 9 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-18 … 2026-11-16: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-22 5.6, 09-23 2.3, 09-24 0.5, 09-25 0.4, 09-26 0.1, 09-27 0.4, 09-28 0.4, 09-29 0.0, 09-30 0.0, 10-01 0.0, 10-02 0.0, 10-03 0.0, 10-04 0.0, 10-05 0.0 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-05 23:47 UTC, updated every 30 minutes.