Examples and guides for using the OpenAI API

Automatic object XML generation for Mujoco

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

Code for the paper "Exploration by Random Network Distillation"

Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"

Code for the paper "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks"