Pinned Loading

1. CSRL CSRL Public

   Code for the experiments of the paper: "Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods" (https://arxiv.org/pdf/2201.12126.pdf))

   Inform 7 2

2. PlaySegmentation-AAAI2025 PlaySegmentation-AAAI2025 Public

   Code for the Paper: Data Augmentation for Instruction Following Policies via Trajectory Segmentation (https://arxiv.org/abs/2503.01871)

   Python 1

3. automatic_scientific_quality_metrics automatic_scientific_quality_metrics Public

   Code for the paper: "Automatic Evaluation Metrics for Artificially Generated Scientific Research" (https://arxiv.org/abs/2503.05712)

   Python

4. OpenReviewParser OpenReviewParser Public

   Parse submissions and reviews from OpenReview into a unified data model with metadata like hypotheses and citations.

   Python

5. UniversalPolicies UniversalPolicies Public

   Code for the paper: "Making Universal Policies Universal" (https://arxiv.org/abs/2502.14777)

   Python