Pinned Loading

1. distillation-after-training distillation-after-training Public

   Official PyTorch implementation of "How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning" (NeurIPS 2025)

   Python

2. four_room four_room Public

   A simple 4-room grid world environment to test generalisation behaviour of RL agents.

   Python 1 1

3. PPO PPO Public

   Implementation of a multiprocessing Proximal Policy Optimization (PPO) algorithm on the BidepalWalker OpenAI Gym environment.

   Python 2

4. DQN DQN Public

   Implements a Double Dueling Deep Q-Network (DQN) in PyTorch

   Python

5. lever-game lever-game Public

   Implements the Lever Coordination Game and shows that the other-play learning algorithm outperforms basic self-play and league-play agents in the zero-shot coordination scenario.

   Jupyter Notebook 1 1

6. PathTracer PathTracer Public

   A multi-threaded implementation of a Path Tracer in C++.

   C++