Pinned Loading

1. CAR-guidance CAR-guidance Public

   Official implementation of Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards (ICML 2026).

   Jupyter Notebook 7

2. SaMI SaMI Public

   Forked from uoe-agents/SaMI

   Official implementation of Skill-aware Mutural Information (SaMI) from the paper Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning.

   Python

3. Skill-aware-Panda-gym Skill-aware-Panda-gym Public

   Forked from uoe-agents/Skill-aware-Panda-gym

   The modified Panda-gym benchmark for evaluating skill-aware RL algorithms.

   Python

4. arlpe arlpe Public

   Basal Glucose Control in Type 1 Diabetes Using An Off-policy Meta Reinforcement Learning Framework with Active Learning

   Python 5 1