Gotta Learn Fast: A new benchmark for generalization in RL

Retro Contest

Variance reduction for policy gradient with action-dependent factorized baselines

Report from the OpenAI hackathon

Improving GANs using optimal transport

On first-order meta-learning algorithms

Reptile: A scalable meta-learning algorithm

OpenAI Scholars

Some considerations on learning to explore via meta-reinforcement learning

Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research

Ingredients for robotics research

OpenAI hackathon