Pinned Loading

1. Zero-Shot-Off-Policy-Learning Zero-Shot-Off-Policy-Learning Public

   Official Pytorch Implementation of "Zero-Shot Off-Policy Learning" (ICML 2026)

   Jupyter Notebook 25 1

2. Deep-Improvement-Supervision Deep-Improvement-Supervision Public

   Official PyTorch implementation of "Latent Reasoning in TRMs is Secretly a Policy Improvement Operator" (ICML 2026)

   Python 23 2

3. Y-Shaped-Generative-Flows Y-Shaped-Generative-Flows Public

   Official Pytorch Implementation of "Y-Shaped Generative Flows"

   Jupyter Notebook 9

4. Partial-Policy-Learning Partial-Policy-Learning Public

   Official JAX implementation of "Rethinking Optimal Transport in Offline Reinforcement Learning" (NeurIPS 2024)

   Python 5 1

5. General-Cost-Neural-Optimal-Transport General-Cost-Neural-Optimal-Transport Public

   Official Pytorch implementation of "Neural Optimal Transport with General Cost Functionals" (ICLR 2024)

   Jupyter Notebook 24 1