2. VdvaeRepository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"
6. Robosumo Code for the paper "Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments"
7. Atari PyA packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface
9. Gpt 2Code for the paper "Language Models are Unsupervised Multitask Learners"
12. EpgCode for the paper "Evolved Policy Gradients"
13. OrrbCode for the paper "OpenAI Remote Rendering Backend"
14. Dall EPyTorch package for the discrete VAE used for DALL·E.
16. RoboschoolDEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.
17. Atari ResetCode for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"
20. BaselinesOpenAI Baselines: high-quality implementations of reinforcement learning algorithms
21. Pixel CnnCode for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"
23. Safety Starter AgentsBasic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
24. Mujoco PyMuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
33. Train ProcgenCode for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"
35. Neural MmoCode for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"
36. Gym3Vectorized interface for reinforcement learning environments
39. Sparse attentionExamples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
40. Multiagent Particle EnvsCode for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
43. Pachi PyPython wrappers for Pachi. Contains a modified version of the bleeding-edge Pachi source code.
44. InfoganCode for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"
47. BlocksparseEfficient GPU kernels for block-sparse matrix multiplication and convolution
48. MaddpgCode for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
49. SpinningupAn educational resource to help anyone learn deep reinforcement learning.