Pinned Loading

1. Farama-Foundation/Metaworld Farama-Foundation/Metaworld Public

   Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

   Python 1.3k 279

2. mil mil Public

   Code for "One-Shot Visual Imitation Learning via Meta-Learning"

   Python 285 70

3. PCGrad PCGrad Public

   Code for "Gradient Surgery for Multi-Task Learning"

   Python 307 34

4. mopo mopo Public

   Code for MOPO: Model-based Offline Policy Optimization

   Python 172 43