Pinned Loading

1. TOP TOP Public

   Implementation of Tactical Optimistic and Pessimistic value estimation

   Python 25 7

2. WNPG WNPG Public

   implementation of Wasserstein Natural Policy Gradients and Wasserstein Natural Evolution Strategies

   Python 13 3

3. first_occupancy first_occupancy Public

   A First Occupancy Representation for Reinforcement Learning

   Jupyter Notebook 2

4. ConstrainedRL4LMs ConstrainedRL4LMs Public

   Forked from allenai/RL4LMs

   A library for constrained RLHF.

   Python 13

5. SimpleCUDA SimpleCUDA Public

   Simple Neural Network in CUDA

   Cuda