#

opsd

Here are 6 public repositories matching this topic...

datawhalechina / agentic-rl-lab

Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.

opd retool opsd gspo alfworld dapo search-r1 agent-rl pytrio harness-rl

Updated Nov 5, 2026
Python

MeiGen-AI / OPSD-V

On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

video-generation opsd autoregressive-generation posttraining

Updated Oct 10, 2026
Python

ZJU-REAL / SDAR

Official code for "Self-Distilled Agentic Reinforcement Learning"

skill rl opsd agentic-ai agentic-skill

Updated Oct 15, 2026
Python

THU-BPM / RLCSD

Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"

reinforcement-learning opd self-distillation opsd large-language-models llm on-policy-distillation

Updated Sep 14, 2026
Python

ZJU-REAL / TTPO

TTPO: Test-Time Policy Optimization

rl reasoning post-training opsd llm test-time-training

Updated Oct 2, 2026
Python

oosei25 / energy-rnn-forecasting

A PyTorch-based, end-to-end energy time-series forecasting demo with LSTM/GRU models, strong seasonal baselines, residual learning, and a CLI for reproducible train/eval runs on OPSD (with run logging + notebooks).

data-science machine-learning energy deep-learning time-series pytorch forcasting electricity-load-forecasting time-series-forecasting rnn-gru rnn-lstm experiment-tracking opsd

Updated Jan 6, 2026
Jupyter Notebook

Add this topic to your repo

To associate your repository with the opsd topic, visit your repo's landing page and select "manage topics."